Lines Matching +full:sense +full:- +full:bitfield +full:- +full:width
1 .. SPDX-License-Identifier: GPL-2.0
4 The Definitive KVM (Kernel-based Virtual Machine) API Documentation
13 - System ioctls: These query and set global attributes which affect the
17 - VM ioctls: These query and set attributes that affect an entire virtual
24 - vcpu ioctls: These query and set attributes that control the operation
32 - device ioctls: These query and set attributes that control the operation
80 facility that allows backward-compatible extensions to the API to be
104 the ioctl returns -ENOTTY.
122 -----------------------
139 -----------------
158 identifier, where IPA_Bits is the maximum width of any physical
159 address used by the VM. The IPA_Bits is encoded in bits[7-0] of the
177 ioctl() at run-time.
189 ----------------------------------------------------------
195 :Returns: 0 on success; -1 on error
231 -----------------------
250 --------------------------
263 the VCPU file descriptor can be mmap-ed, including:
265 - if KVM_CAP_COALESCED_MMIO is available, a page at
270 - if KVM_CAP_DIRTY_LOG_RING is available, a number of pages at
276 -------------------------
282 :Returns: 0 on success, -1 on error
288 -------------------
294 :Returns: vcpu fd on success, -1 on error
300 the KVM_CHECK_EXTENSION ioctl() at run-time.
302 KVM_CAP_MAX_VCPUS of the KVM_CHECK_EXTENSION ioctl() at run-time.
310 KVM_CAP_MAX_VCPU_ID of the KVM_CHECK_EXTENSION ioctl() at run-time.
325 single-threaded guest vcpus, it should make all vcpu ids be a multiple
335 --------------------------------
341 :Returns: 0 on success, -1 on error
360 If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of slot field specifies
372 ------------------------
378 :Returns: 0 (success), -1 (error)
384 ------------
390 :Returns: 0 on success, -1 on error
411 -----------------
417 :Returns: 0 on success, -1 on error
444 -----------------
450 :Returns: 0 on success, -1 on error
458 ------------------
464 :Returns: 0 on success, -1 on error
481 /* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */
489 ------------------
495 :Returns: 0 on success, -1 on error
502 ------------------
508 :Returns: 0 on success, -1 on error
529 ------------------
554 -EEXIST if an interrupt is already enqueued
555 -EINVAL the irq number is invalid
556 -ENXIO if the PIC is in the kernel
557 -EFAULT if the pointer is invalid
561 ioctl is useful if the in-kernel PIC is not used.
601 RISC-V:
620 --------------------
626 :Returns: -1 on error
632 -----------------
639 -1 on error
642 Reads the values of MSR-based features that are available for the VM. This
644 The list of msr-based features can be obtained using KVM_GET_MSR_FEATURE_INDEX_LIST
648 Reads model-specific registers from the vcpu. Supported msr indices can
672 -----------------
678 :Returns: number of msrs successfully set (see below), -1 on error
680 Writes model-specific registers to the vcpu. See KVM_GET_MSRS for the
694 ------------------
700 :Returns: 0 on success, -1 on error
706 - If this IOCTL fails, KVM gives no guarantees that previous valid CPUID
709 - Using KVM_SET_CPUID{,2} after KVM_RUN, i.e. changing the guest vCPU model
711 - Using heterogeneous CPUID configurations, modulo APIC IDs, topology, etc...
734 ------------------------
740 :Returns: 0 on success, -1 on error
745 their traditional behaviour) will cause KVM_RUN to return with -EINTR.
760 ----------------
766 :Returns: 0 on success, -1 on error
789 ----------------
795 :Returns: 0 on success, -1 on error
818 -----------------------
824 :Returns: 0 on success, -1 on error
828 future vcpus to have a local APIC. IRQ routing for GSIs 0-15 is set to both
829 PIC and IOAPIC; GSI 16-23 only go to the IOAPIC.
840 -----------------
846 :Returns: 0 on success, -1 on error
850 been previously created with KVM_CREATE_IRQCHIP. Note that edge-triggered
853 On real hardware, interrupt pins can be active-low or active-high. This
858 (active-low/active-high) for level-triggered interrupts, and KVM used
860 active-low interrupts, the above convention is now valid on x86 too.
862 should not present interrupts to the guest as active-low unless this
863 capability is present (or unless it is not using the in-kernel irqchip,
868 in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to
877 - irq_type[0]:
878 out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ
879 - irq_type[1]:
880 in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.)
882 - irq_type[2]:
883 in-kernel GIC: PPI, irq_id between 16 and 31 (incl.)
894 injection of interrupts for the in-kernel irqchip. KVM_IRQ_LINE can always
909 --------------------
915 :Returns: 0 on success, -1 on error
934 --------------------
940 :Returns: 0 on success, -1 on error
959 -----------------------
965 :Returns: 0 on success, -1 on error
970 page of a blob (32- or 64-bit, depending on the vcpu mode) to guest
1005 ------------------
1011 :Returns: 0 on success, -1 on error
1055 ------------------
1061 :Returns: 0 on success, -1 on error
1090 ------------------------
1097 :Returns: 0 on success, -1 on error
1142 - KVM_VCPUEVENT_VALID_SHADOW may be set to signal that
1145 - KVM_VCPUEVENT_VALID_SMM may be set to signal that smi contains a
1148 - KVM_VCPUEVENT_VALID_PAYLOAD may be set to signal that the
1153 - KVM_VCPUEVENT_VALID_TRIPLE_FAULT may be set to signal that the
1172 guest-visible registers. It is not possible to 'cancel' an SError that has been
1175 A device being emulated in user-space may also wish to generate an SError. To do
1176 this the events structure can be populated by user-space. The current state
1185 always have a non-zero value when read, and the agent making an SError pending
1187 the system supports KVM_CAP_ARM_INJECT_SERROR_ESR, but user-space sets the events
1191 -EINVAL. Setting anything other than the lower 24bits of exception.serror_esr
1192 will return -EINVAL.
1213 ------------------------
1220 :Returns: 0 on success, -1 on error
1233 suppress overwriting the current in-kernel state. The bits are:
1238 KVM_VCPUEVENT_VALID_SMM transfer the smi sub-struct.
1280 ----------------------
1286 :Returns: 0 on success, -1 on error
1302 ----------------------
1308 :Returns: 0 on success, -1 on error
1317 -------------------------------
1323 :Returns: 0 on success, -1 on error
1340 memory slot. Bits 0-15 of "slot" specify the slot id and this value
1345 If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
1372 to make a new slot read-only. In this case, writes to this memory will be
1386 ---------------------
1392 :Returns: 0 on success, -1 on error
1394 This ioctl defines the physical address of a three-page region in the guest
1400 This ioctl is required on Intel-based hosts. This is needed on Intel hardware
1406 -------------------
1412 :Returns: 0 on success; -1 on error
1418 :Returns: 0 on success; -1 on error
1443 A bitfield indicating future enhancements. Has to be 0 for now.
1457 The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl
1458 for vm-wide capabilities.
1461 ---------------------
1467 :Returns: 0 on success; -1 on error
1502 in-kernel irqchip, the multiprocessing state must be maintained by userspace on
1539 ---------------------
1545 :Returns: 0 on success; -1 on error
1551 in-kernel irqchip, the multiprocessing state must be maintained by userspace on
1561 ------------------------------
1567 :Returns: 0 on success, -1 on error
1569 This ioctl defines the physical address of a one-page region in the guest
1578 This ioctl is required on Intel-based hosts. This is needed on Intel hardware
1585 ------------------------
1591 :Returns: 0 on success, -1 on error
1600 ------------------
1606 :Returns: 0 on success, -1 on error
1620 ------------------
1626 :Returns: 0 on success, -1 on error
1648 -----------------
1654 :Returns: 0 on success, -1 on error
1675 -----------------
1681 :Returns: 0 on success, -1 on error
1702 ----------------------------
1708 :Returns: 0 on success, -1 on error
1741 Dynamically-enabled feature bits need to be requested with
1751 with the 'nent' field indicating the number of entries in the variable-size
1791 -----------------------
1821 ------------------------
1827 :Returns: 0 on success, -1 on error
1833 - GSI routing does not apply to KVM_IRQ_LINE but only to KVM_IRQFD.
1871 - KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry
1872 type, specifies that the devid field contains a valid value. The per-VM
1876 - zero otherwise
1901 address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of
1935 --------------------
1941 :Returns: 0 on success, -1 on error
1951 --------------------
1957 :Returns: virtual tsc-khz on success, negative value on error
1960 KHz. If the host has unstable tsc this ioctl returns -EIO instead as an
1965 ------------------
1971 :Returns: 0 on success, -1 on error
1986 the APIC_ID register (bytes 32-35). xAPIC only allows an 8-bit APIC ID
1987 which is stored in bits 31-24 of the APIC register, or equivalently in
1996 ------------------
2002 :Returns: 0 on success, -1 on error
2014 The format of the APIC ID register (bytes 32-35 of struct kvm_lapic_state's
2020 ------------------
2043 For the special case of virtio-ccw devices on s390, the ioevent is matched
2057 For virtio-ccw devices, addr contains the subchannel id and datamatch the
2066 ------------------
2072 :Returns: 0 on success, -1 on error
2092 The array is little-endian: the bit 0 is the least significant bit of the
2102 -------------------------
2111 is an IOMMU for PAPR-style virtual I/O. It is used to translate
2125 which this TCE table will translate - the table will contain one 64
2135 the entries written by kernel-handled H_PUT_TCE calls, and also lets
2141 ---------------------
2150 time by the kernel. An RMA is a physically-contiguous, aligned region
2152 will be accessed by real-mode (MMU off) accesses in a KVM guest.
2177 ------------
2183 :Returns: 0 on success, -1 on error
2193 - pause the vcpu
2194 - read the local APIC's state (KVM_GET_LAPIC)
2195 - check whether changing LINT1 will queue an NMI (see the LVT entry for LINT1)
2196 - if so, issue KVM_NMI
2197 - resume the vcpu
2204 ----------------------
2226 ------------------------
2248 ------------------------
2266 --------------------
2298 and their own constants and width. To keep track of the implemented
2302 Arch Register Width (bits)
2504 ARM 32-bit CP15 registers have the following id bit patterns::
2508 ARM 64-bit CP15 registers have the following id bit patterns::
2516 ARM 32-bit VFP control registers have the following id bit patterns::
2520 ARM 64-bit FP registers have the following id bit patterns::
2524 ARM firmware pseudo-registers have the following bit pattern::
2532 arm64 core/FP-SIMD registers have the following id bit patterns. Note
2566 .. [1] These encodings are not accepted for SVE-enabled vcpus. See
2591 arm64 firmware pseudo-registers have the following bit pattern::
2600 0x6060 0000 0015 ffff KVM_REG_ARM64_SVE_VLS pseudo-register
2603 ENOENT. max_vq is the vcpu's maximum supported vector length in 128-bit
2614 KVM_REG_ARM64_SVE_VLS is a pseudo-register that allows the set of vector
2624 ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >>
2625 ((vq - KVM_ARM64_SVE_VQ_MIN) % 64)) & 1))
2647 is hardware-dependent and may not be available. Attempting to configure
2654 arm64 bitmap feature firmware pseudo-registers have the following bit pattern::
2668 a -EBUSY to userspace.
2681 patterns depending on whether they're 32-bit or 64-bit registers::
2683 0x7020 0000 0001 00 <reg:5> <sel:3> (32-bit)
2684 0x7030 0000 0001 00 <reg:5> <sel:3> (64-bit)
2709 0x7020 0000 0003 00 <0:3> <reg:5> (32-bit FPU registers)
2710 0x7030 0000 0003 00 <0:3> <reg:5> (64-bit FPU registers)
2711 0x7040 0000 0003 00 <0:3> <reg:5> (128-bit MSA vector registers)
2723 RISC-V registers are mapped using the lower 32 bits. The upper 8 bits of
2726 RISC-V config registers are meant for configuring a Guest VCPU and it has
2732 Following are the RISC-V config registers:
2744 RISC-V core registers represent the general excution state of a Guest VCPU
2750 Following are the RISC-V core registers:
2787 0x80x0 0000 0200 0020 mode Privilege mode (1 = S-mode or 0 = U-mode)
2790 RISC-V csr registers represent the supervisor mode control/status registers
2796 Following are the RISC-V csr registers:
2812 RISC-V timer registers represent the timer state of a Guest VCPU and it has
2817 Following are the RISC-V timer registers:
2822 0x8030 0000 0400 0000 frequency Time base frequency (read-only)
2828 RISC-V F-extension registers represent the single precision floating point
2833 Following are the RISC-V F-extension registers:
2844 RISC-V D-extension registers represent the double precision floating point
2848 0x8030 0000 06 <index into the __riscv_d_ext_state struct:24> (non-fcsr)
2850 Following are the RISC-V D-extension registers:
2863 --------------------
2893 ----------------------
2899 :Returns: 0 on success, -1 on error
2910 load-link/store-conditional, or equivalent must be used. There are two cases
2917 -------------------
2923 :Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
2925 Directly inject a MSI message. Only valid with in-kernel irqchip that handles
2940 KVM_MSI_VALID_DEVID: devid contains a valid value. The per-VM
2951 address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of
2956 --------------------
2962 :Returns: 0 on success, -1 on error
2964 Creates an in-kernel device model for the i8254 PIT. This call is only valid
2965 after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following
2977 PIT timer interrupts may use a per-VM kernel thread for injection. If it
2980 kvm-pit/<owner-process-pid>
2989 -----------------
2995 :Returns: 0 on success, -1 on error
2997 Retrieves the state of the in-kernel PIT model. Only valid after
3017 -----------------
3023 :Returns: 0 on success, -1 on error
3025 Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2.
3032 --------------------------
3038 :Returns: 0 on success, -1 on error
3043 device-tree properties for the guest operating system.
3057 - KVM_PPC_PAGE_SIZES_REAL:
3062 - KVM_PPC_1T_SEGMENTS
3066 - KVM_PPC_NO_HASH
3107 --------------
3113 :Returns: 0 on success, -1 on error
3123 With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD supports a de-assert and notify
3124 mechanism allowing emulation of level-triggered, irqfd-based
3129 as from an EOI, the gsi is de-asserted and the user is notified via
3130 kvm_irqfd.resamplefd. It is the user's responsibility to re-queue
3138 - in case no routing entry is associated to this gsi, injection fails
3139 - in case the gsi is associated to an irqchip routing entry,
3141 - in case the gsi is associated to an MSI routing entry, the MSI
3143 to GICv3 ITS in-kernel emulation).
3146 --------------------------
3152 :Returns: 0 on success, -1 on error
3164 The parameter is a pointer to a 32-bit unsigned integer variable
3171 default-sized hash table (16 MB).
3179 real-mode area (VRMA) facility, the kernel will re-create the VMRA
3183 -----------------------
3189 :Returns: 0 on success, -1 on error
3205 - sigp stop; optional flags in parm
3207 - program check; code in parm
3209 - sigp set prefix; prefix address in parm
3211 - restart
3213 - clock comparator interrupt
3215 - CPU timer interrupt
3217 - virtio external interrupt; external interrupt
3220 - sclp external interrupt; sclp parameter in parm
3222 - sigp emergency; source cpu in parm
3224 - sigp external call; source cpu in parm
3226 - compound value to indicate an
3227 I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel);
3231 - machine check interrupt; cr 14 bits in parm, machine check interrupt
3238 ------------------------
3244 :Returns: file descriptor number (>= 0) on success, -1 on error
3293 ----------------------
3298 :Returns: 0 on success, -1 on error
3331 --------------------------------------------
3338 :Returns: 0 on success, -1 on error
3346 (e.g. read-only attribute, or attribute that only makes
3347 sense when the device is in a different state)
3353 semantics are device-specific. See individual device documentation in
3361 __u32 group; /* device-defined */
3362 __u64 attr; /* group-defined */
3367 ------------------------
3374 :Returns: 0 on success, -1 on error
3389 ----------------------
3395 :Returns: 0 on success; -1 on error
3410 - Processor state:
3415 - General Purpose registers, including PC and SP: set to 0
3416 - FPSIMD/NEON registers: set to 0
3417 - SVE registers: set to 0
3418 - System registers: Reset to their architecturally defined
3431 - KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
3434 - KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
3436 - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 (or a future revision
3439 - KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
3442 - KVM_ARM_VCPU_PTRAUTH_ADDRESS: Enables Address Pointer authentication
3450 - KVM_ARM_VCPU_PTRAUTH_GENERIC: Enables Generic Pointer authentication
3458 - KVM_ARM_VCPU_SVE: Enables SVE for the CPU (arm64 only).
3464 - KVM_REG_ARM64_SVE_VLS may be read using KVM_GET_ONE_REG: the
3465 initial value of this pseudo-register indicates the best set of
3470 - KVM_RUN and KVM_GET_REG_LIST are not available;
3472 - KVM_GET_ONE_REG and KVM_SET_ONE_REG cannot be used to access
3477 - KVM_REG_ARM64_SVE_VLS may optionally be written using
3483 - the KVM_REG_ARM64_SVE_VLS pseudo-register is immutable, and can
3487 -----------------------------
3493 :Returns: 0 on success; -1 on error
3506 kvm_vcpu_init->features bitmap returned will have feature bits set if
3516 ---------------------
3522 :Returns: 0 on success; -1 on error
3543 -----------------------------------------
3549 :Returns: 0 on success, -1 on error
3579 arm64 currently only require this when using the in-kernel GIC
3585 base addresses will return -EEXIST.
3592 ------------------------------
3598 :Returns: 0 on success, -1 on error
3603 of a service that has a kernel-side implementation. If the token
3604 value is non-zero, it will be associated with that service, and
3612 ------------------------
3618 :Returns: 0 on success; -1 on error
3630 first a control bitfield indicates the type of debug events to handle
3633 - KVM_GUESTDBG_ENABLE: guest debugging is enabled
3634 - KVM_GUESTDBG_SINGLESTEP: the next run should single-step
3639 - KVM_GUESTDBG_USE_SW_BP: using software breakpoints [x86, arm64]
3640 - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390]
3641 - KVM_GUESTDBG_USE_HW: using hardware debug events [arm64]
3642 - KVM_GUESTDBG_INJECT_DB: inject DB type exception [x86]
3643 - KVM_GUESTDBG_INJECT_BP: inject BP type exception [x86]
3644 - KVM_GUESTDBG_EXIT_PENDING: trigger an immediate guest exit [s390]
3645 - KVM_GUESTDBG_BLOCKIRQ: avoid injecting interrupts/NMI/SMI [x86]
3663 the single-step debug event (KVM_GUESTDBG_SINGLESTEP) is supported.
3673 ---------------------------
3679 :Returns: 0 on success, -1 on error
3714 the variable-size array 'entries'. If the number of entries is too low
3748 --------------------
3755 < 0 on generic error (e.g. -EFAULT or -ENOMEM),
3810 Logical accesses are permitted for non-protected guests only.
3828 translation-exception identifier (TEID) indicates suppression.
3851 Absolute accesses are permitted for non-protected guests only.
3871 -----------------------
3897 will cause the ioctl to return -EINVAL.
3903 -----------------------
3921 will cause the ioctl to return -EINVAL.
3928 the ioctl will return -EINVAL.
3931 -----------------
3937 :Returns: 0 on success, -1 on error
3978 - KVM_S390_SIGP_STOP - sigp stop; parameter in .stop
3979 - KVM_S390_PROGRAM_INT - program check; parameters in .pgm
3980 - KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix
3981 - KVM_S390_RESTART - restart; no parameters
3982 - KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters
3983 - KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters
3984 - KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg
3985 - KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall
3986 - KVM_S390_MCHK - machine check interrupt; parameters in .mchk
3991 ---------------------------
3998 -EINVAL if buffer size is 0,
3999 -ENOBUFS if buffer size is too small to fit all pending interrupts,
4000 -EFAULT if the buffer address was invalid
4018 the kernel never checked for flags == 0 and QEMU never pre-zeroed flags and
4022 If -ENOBUFS is returned the buffer provided was too small and userspace
4026 ---------------------------
4033 -EFAULT if the buffer address was invalid,
4034 -EINVAL for an invalid buffer length (see below),
4035 -EBUSY if there were already interrupts pending,
4039 This ioctl allows userspace to set the complete state of all cpu-local
4061 which is the maximum number of possibly pending cpu-local interrupts.
4064 ------------
4070 :Returns: 0 on success, -1 on error
4075 ----------------------------
4142 default KVM in-kernel emulation behavior is fully preserved.
4182 ----------------------------
4215 -------------------------
4222 -EFAULT if struct kvm_reinject_control cannot be read,
4223 -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier.
4242 ------------------------------
4249 -EFAULT if struct kvm_ppc_mmuv3_cfg cannot be read,
4250 -EINVAL if the configuration is invalid
4276 ---------------------------
4283 -EFAULT if struct kvm_ppc_rmmu_info cannot be written,
4284 -EINVAL if no useful information can be returned
4313 --------------------------------
4322 -EFAULT if struct kvm_reinject_control cannot be read,
4323 -EINVAL if the supplied shift or flags are invalid,
4324 -ENOMEM if unable to allocate the new HPT,
4357 returns 0 (i.e. cancels any in-progress preparation).
4360 flags will result in an -EINVAL.
4367 -------------------------------
4374 -EFAULT if struct kvm_reinject_control cannot be read,
4375 -EINVAL if the supplied shift or flags are invalid,
4376 -ENXIO is there is no pending HPT, or the pending HPT doesn't
4378 -EBUSY if the pending HPT is not fully prepared,
4379 -ENOSPC if there was a hash collision when moving existing
4381 -EIO on other error conditions
4398 KVM_PPC_RESIZE_HPT_COMMIT will return an error (usually -ENXIO or
4399 -EBUSY, though others may be possible if the preparation was started,
4412 -----------------------------------
4418 :Returns: 0 on success, -1 on error
4425 -----------------------
4432 -EFAULT if u64 mcg_cap cannot be read,
4433 -EINVAL if the requested number of banks is invalid,
4434 -EINVAL if requested MCE capability is not supported.
4439 supported number of error-reporting banks can be retrieved when
4444 ---------------------
4451 -EFAULT if struct kvm_x86_mce cannot be read,
4452 -EINVAL if the bank number is invalid,
4453 -EINVAL if VAL bit is not set in status field.
4478 ----------------------------
4489 - During live migration to save the CMMA values. Live migration needs
4491 - To non-destructively peek at the CMMA values, with the flag
4522 KVM_S390_SKEYS_MAX. KVM_S390_SKEYS_MAX is re-used for consistency with
4566 This ioctl can fail with -ENOMEM if not enough memory can be allocated to
4567 complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if
4569 -EFAULT if the userspace address is invalid or if no page table is
4573 ----------------------------
4612 This ioctl can fail with -ENOMEM if not enough memory can be allocated to
4613 complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if
4615 if the flags field was not 0, with -EFAULT if the userspace address is
4621 --------------------------
4628 -EFAULT if struct kvm_ppc_cpu_char cannot be written
4633 CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754). The information is
4650 with preventing inadvertent information disclosure - specifically,
4651 whether there is an instruction to flash-invalidate the L1 data cache
4668 ---------------------------
4674 :Returns: 0 on success; -1 on error
4677 for issuing platform-specific memory encryption commands to manage those
4682 Documentation/virt/kvm/x86/amd-memory-encryption.rst.
4685 -----------------------------------
4691 :Returns: 0 on success; -1 on error
4696 It is used in the SEV-enabled guest. When encryption is enabled, a guest
4709 -------------------------------------
4715 :Returns: 0 on success; -1 on error
4721 ------------------------
4729 the specified Hyper-V connection id through the SIGNAL_EVENT hypercall, without
4730 causing a user exit. SIGNAL_EVENT hypercall with non-zero event flag number
4731 (bits 24-31) still triggers a KVM_EXIT_HYPERV_HCALL user exit.
4751 -EINVAL if conn_id or flags is outside the allowed range,
4752 -ENOENT on deassign if the conn_id isn't registered,
4753 -EEXIST on assign if the conn_id is already registered
4756 --------------------------
4762 :Returns: 0 on success, -1 on error
4830 --------------------------
4836 :Returns: 0 on success, -1 on error
4842 -------------------------------------
4871 ------------------------------------
4877 :Returns: 0 on success, -1 on error
4899 in KVM's dirty bitmap, and dirty tracking is re-enabled for that page
4900 (for example via write-protection, or by clearing the dirty bit in
4903 If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of slot field specifies
4913 --------------------------------
4919 :Returns: 0 on success, -1 on error
4940 This ioctl returns x86 cpuid features leaves related to Hyper-V emulation in
4942 cpuid information presented to guests consuming Hyper-V enlightenments (e.g.
4943 Windows or Hyper-V guests).
4945 CPUID feature leaves returned by this ioctl are defined by Hyper-V Top Level
4952 - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS
4953 - HYPERV_CPUID_INTERFACE
4954 - HYPERV_CPUID_VERSION
4955 - HYPERV_CPUID_FEATURES
4956 - HYPERV_CPUID_ENLIGHTMENT_INFO
4957 - HYPERV_CPUID_IMPLEMENT_LIMITS
4958 - HYPERV_CPUID_NESTED_FEATURES
4959 - HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS
4960 - HYPERV_CPUID_SYNDBG_INTERFACE
4961 - HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES
4964 with the 'nent' field indicating the number of entries in the variable-size
4965 array 'entries'. If the number of entries is too low to describe all Hyper-V
4967 to the number of Hyper-V feature leaves, the 'nent' field is adjusted to the
4977 - HYPERV_CPUID_NESTED_FEATURES leaf and HV_X64_ENLIGHTENED_VMCS_RECOMMENDED
4980 - HV_STIMER_DIRECT_MODE_AVAILABLE bit is only exposed with in-kernel LAPIC.
4984 ---------------------------
4989 :Returns: 0 on success, -1 on error
5015 that should be performaned and how to do it are feature-dependent.
5019 -EPERM unless the feature has already been finalized by means of a
5026 ------------------------------
5032 :Returns: 0 on success, -1 on error
5060 ---------------------
5084 ---------------------------
5096 ----------------------------
5109 --------------------------
5123 -------------------------
5168 again. All registered VCPUs are converted back to non-protected
5266 not succeed all other subcommands will fail with -EINVAL. This
5267 subcommand will return -EINVAL if a dump process has not yet been
5293 --------------------------
5337 Sets the ABI mode of the VM to 32-bit or 64-bit (long mode). This
5361 This is the HVM-wide vector injected directly by the hypervisor
5380 the 32-bit version code returned to the guest when it invokes the
5387 --------------------------
5400 ---------------------------
5467 other four times. The state field must be set to -1, or to a valid
5475 vCPU ID of the given vCPU, to allow timer-related VCPU operations to
5487 per-vCPU local APIC upcall vector, configured by a Xen guest with
5489 used by Windows guests, and is distinct from the HVM-wide upcall
5494 ---------------------------
5509 ---------------------------
5515 :Returns: number of bytes copied, < 0 on error (-EINVAL for incorrect
5516 arguments, -EFAULT if memory cannot be accessed).
5546 --------------------
5552 :Returns: 0 on success, -1 on error
5579 --------------------
5585 :Returns: 0 on success, -1 on error
5592 ----------------------
5611 +-------------+
5613 +-------------+
5615 +-------------+
5617 +-------------+
5619 +-------------+
5709 Bits 0-3 of ``flags`` encode the type:
5731 is [``hist_param``*(N-1), ``hist_param``*N), while the range of the last
5732 bucket is [``hist_param``*(``size``-1), +INF). (+INF means positive infinity
5737 [0, 1), while the range of the last bucket is [pow(2, ``size``-2), +INF).
5739 [pow(2, N-2), pow(2, N-1)).
5741 Bits 4-7 of ``flags`` encode the unit:
5764 Bits 8-11 of ``flags``, together with ``exponent``, encode the scale of the
5769 CPU clock cycles. For example, an exponent of -9 can be used with
5785 bucket in the unit expressed by bits 4-11 of ``flags`` together with ``exponent``.
5791 The Stats Data block contains an array of 64-bit values in the same order
5795 --------------------
5801 :Returns: 0 on success, -1 on error
5822 -----------------------------
5842 -----------------------------
5851 for vcpus. It re-uses the kvm_s390_pv_dmp struct and hence also shares
5867 ----------------------
5875 Used to manage hardware-assisted virtualization features for zPCI devices.
5935 This field is polled once when KVM_RUN starts; if non-zero, KVM_RUN
5936 exits immediately, returning -EINTR. In the common scenario where a
5940 a signal handler that sets run->immediate_exit to a non-zero value.
5966 The value of the current interrupt flag. Only valid if in-kernel
5973 More architecture-specific flags detailing state of the VCPU that may
5988 The value of the cr8 register. Only valid if in-kernel local APIC is
5995 The value of the APIC BASE msr. Only valid if in-kernel local
6007 reasons. Further architecture-specific information is available in
6019 to unknown reasons. Further architecture-specific information is
6072 executed a memory-mapped I/O instruction which could not be satisfied
6077 appear if the VCPU performed a load or store of the appropriate width directly
6085 has re-entered the kernel with KVM_RUN. The kernel side will first finish
6090 completed before performing a live migration. Userspace can re-enter the
6172 Deprecated - was used for 440 KVM.
6198 This is used on 64-bit PowerPC when emulating a pSeries partition,
6202 the arguments (from the guest R4 - R12). Userspace should put the
6263 a system-level event using some architecture specific mechanism (hypercall
6267 The 'type' field describes the system-level event type.
6270 - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the
6274 - KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
6277 - KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest
6281 - KVM_SYSTEM_EVENT_SEV_TERM -- an AMD SEV guest requested termination.
6283 - KVM_SYSTEM_EVENT_WAKEUP -- the exiting vCPU is in a suspended state and
6286 - KVM_SYSTEM_EVENT_SUSPEND -- the guest has requested a suspension of
6290 architecture specific information for the system-level event. Only
6293 - for arm64, data[0] is set to KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 if
6297 - for RISC-V, data[0] is set to the value of the second argument of the
6305 --------------
6315 the call parameters are left in-place in the vCPU registers.
6320 - Honor the guest request to suspend the VM. Userspace can request
6321 in-kernel emulation of suspension by setting the calling vCPU's
6327 - Deny the guest request to suspend the VM. See ARM DEN0022D.b 5.19.2
6337 Indicates that the VCPU's in-kernel local APIC received an EOI for a
6338 level-triggered IOAPIC interrupt. This exit only triggers when the
6380 related to Hyper-V emulation.
6384 - KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about
6386 Hyper-V SynIC state change. Notification is used to remap SynIC
6390 - KVM_EXIT_HYPERV_SYNDBG -- synchronously notify user-space about
6392 Hyper-V Synthetic debugger state change. Notification is used to either update
6411 the VM. KVM assumed that if the guest accessed non-memslot memory, it was
6434 __u8 error; /* user -> kernel */
6436 __u32 reason; /* kernel -> user */
6437 __u32 index; /* kernel -> user */
6438 __u64 data; /* kernel <-> user */
6450 KVM_MSR_EXIT_REASON_UNKNOWN - access to MSR that is unknown to KVM
6451 KVM_MSR_EXIT_REASON_INVAL - access to invalid MSRs or reserved bits
6452 KVM_MSR_EXIT_REASON_FILTER - access blocked by KVM_X86_SET_MSR_FILTER
6492 - KVM_EXIT_XEN_HCALL -- synchronously notify user-space about Xen hypercall.
6507 done a SBI call which is not handled by KVM RISC-V kernel module. The details
6513 values of SBI call before resuming the VCPU. For more details on RISC-V SBI
6514 spec refer, https://github.com/riscv/riscv-sbi-doc.
6525 enabled, a VM exit generated if no event window occurs in VM non-root mode
6533 - KVM_NOTIFY_CONTEXT_INVALID -- the VM context is corrupted and not valid
6589 whether this is a per-vcpu or per-vm capability.
6600 -------------------
6605 :Returns: 0 on success; -1 on error
6609 were invented by Mac-on-Linux to have a standardized communication mechanism
6616 --------------------
6621 :Returns: 0 on success; -1 on error
6637 ------------------
6642 :Returns: 0 on success; -1 on error
6655 addresses of mmu-type-specific data structures. The "array_len" field is an
6671 - The "params" field is of type "struct kvm_book3e_206_tlb_params".
6672 - The "array" field points to an array of type "struct
6674 - The array consists of all entries in the first TLB, followed by all
6676 - Within a TLB, entries are ordered first by increasing set number. Within a
6678 - The hash for determining set number in TLB0 is: (MAS2 >> 12) & (num_sets - 1)
6680 - The tsize field of mas1 shall be set to 4K on TLB0, even though the
6684 ----------------------------
6689 :Returns: 0 on success; -1 on error
6694 handled in-kernel, while the other I/O instructions are passed to userspace.
6699 Note that even though this capability is enabled per-vcpu, the complete
6703 -------------------
6708 :Returns: 0 on success; -1 on error
6722 --------------------
6728 This capability connects the vcpu to an in-kernel MPIC device.
6731 --------------------
6738 This capability connects the vcpu to an in-kernel XICS device.
6741 ------------------------
6747 This capability enables the in-kernel irqchip for s390. Please refer to
6751 --------------------
6765 ---------------------
6778 ----------------------
6783 :Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register
6799 - the register sets to be copied out to kvm_run are selectable
6801 - vcpu_events are available in addition to regs and sregs.
6804 function as an input bit-array field set by userspace to indicate the
6824 -------------------------
6831 This capability connects the vcpu to an in-kernel XIVE device.
6856 ----------------------------
6860 args[1] is 0 to disable, 1 to enable in-kernel handling
6863 get handled by the kernel or not. Enabling or disabling in-kernel
6865 initial set of hcalls are enabled for in-kernel handling, which
6866 consists of those hcalls for which in-kernel handlers were implemented
6869 to handle it. Note that it may not make sense to enable some and
6873 If the hcall number specified is not one that has an in-kernel
6878 --------------------------
6887 - SENSE
6888 - SENSE RUNNING
6889 - EXTERNAL CALL
6890 - EMERGENCY SIGNAL
6891 - CONDITIONAL EMERGENCY SIGNAL
6900 ---------------------------------
6908 return -EINVAL if the machine does not support vectors.
6911 --------------------------
6916 This capability allows post-handlers for the STSI instruction. After
6921 vcpu->run::
6932 @addr - guest address of STSI SYSIB
6933 @fc - function code
6934 @sel1 - selector 1
6935 @sel2 - selector 2
6936 @ar - access register number
6938 KVM handlers should exit to userspace with rc = -EREMOTE.
6941 -------------------------
6944 :Parameters: args[0] - number of routes reserved for userspace IOAPICs
6945 :Returns: 0 on success, -1 on error
6962 -------------------
6967 Allows use of runtime-instrumentation introduced with zEC12 processor.
6968 Will return -EINVAL if the machine does not support runtime-instrumentation.
6969 Will return -EBUSY if a VCPU has already been created.
6972 ----------------------
6975 :Parameters: args[0] - features that should be enabled
6976 :Returns: 0 on success, -EINVAL when args[0] contains invalid features
6985 allowing the use of 32-bit APIC IDs. See KVM_CAP_X2APIC_API in their
6992 where 0xff represents CPUs 0-7 in cluster 0.
6995 ----------------------------
7002 mechanism e.g. to realize 2-byte software breakpoints. The kernel will
7010 -------------------
7014 :Returns: 0 on success; -EINVAL if the machine does not support
7015 guarded storage; -EBUSY if a VCPU has already been created.
7020 ---------------------
7025 Allow use of adapter-interruption suppression.
7026 :Returns: 0 on success; -EBUSY if a VCPU has already been created.
7029 --------------------
7047 ----------------------
7059 ------------------------------
7063 :Returns: 0 on success, -EINVAL when args[0] contains invalid exits
7082 --------------------------
7086 :Returns: 0 on success, -EINVAL if hpage module parameter was not set
7094 hpage module parameter is not set to 1, -EINVAL is returned.
7100 ------------------------------
7110 --------------------------
7114 :Returns: 0 on success, -EINVAL when the implementation doesn't support
7115 nested-HV virtualization.
7117 HV-KVM on POWER9 and later systems allows for "nested-HV"
7119 can run using the CPU's supervisor mode (privileged non-hypervisor
7122 kvm-hv module parameter.
7125 ------------------------------
7131 emulated VM-exit when L1 intercepts a #PF exception that occurs in
7132 L2. Similarly, for kvm-intel only, DR6 will not be modified prior to
7133 the emulated VM-exit when L1 intercepts a #DB exception that occurs in
7139 exception.has_payload and to put the faulting address - or the new DR6
7140 bits\ [#]_ - in the exception_payload field.
7161 automatically clear and write-protect all pages that are returned as dirty.
7167 KVM_CLEAR_DIRTY_LOG ioctl can operate on a 64-page granularity rather
7192 ------------------------------
7209 ----------------------
7214 :Returns: 0 on success; -1 on error
7217 maximum halt-polling time for all vCPUs in the target VM. This capability can
7219 maximum halt-polling time.
7221 See Documentation/virt/kvm/halt-polling.rst for more information on halt
7225 -------------------------------
7230 :Returns: 0 on success; -1 on error
7247 -------------------------------
7252 :Returns: 0 on success, -EINVAL when args[0] contains invalid bits
7278 KVM_RUN_BUS_LOCK flag in vcpu-run->flags field and exit to userspace. Concerning
7284 ----------------------
7288 :Returns: 0 on success, -EINVAL when CPU doesn't support 2nd DAWR
7295 -------------------------------------
7305 This is intended to support in-guest workloads scheduled by the host. This
7306 allows the in-guest workload to maintain its own NPTs and keeps the two vms
7311 --------------------------
7316 :Returns: 0 on success, -EINVAL if the file handle is invalid or if a requested
7334 -------------------------------
7345 IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is
7346 present in the "ibm,hypertas-functions" device-tree property.
7352 --------------------------------------
7370 --------------------
7387 not-shareable (no MAP_SHARED), attempts to create a memslot with a
7388 MAP_SHARED mmap will result in an -EINVAL return.
7394 -------------------------------------
7404 This is intended to support intra-host migration of VMs between userspace VMMs,
7408 -------------------------------
7418 This capability allows a guest kernel to use a better-performance mode for
7422 ----------------------------
7425 :Parameters: args[0] - set of KVM quirks to disable
7457 KVM_X86_QUIRK_OUT_7E_INC_RIP By default, KVM pre-increments %rip before
7460 KVM does not pre-increment %rip before
7494 ------------------------
7498 :Parameters: args[0] - maximum APIC ID value set for current VM
7499 :Returns: 0 on success, -EINVAL if args[0] is beyond KVM_MAX_VCPU_IDS
7515 ------------------------------
7520 :Returns: 0 on success, -EINVAL if args[0] contains invalid flags or notify
7530 in per-VM scope during VM creation. Notify VM exit is disabled by default.
7533 a VM exit if no event window occurs in VM non-root mode for a specified of
7550 ---------------------
7556 H_RANDOM hypercall backed by a hardware random-number generator.
7561 ------------------------
7567 Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is
7568 used to support Windows Hyper-V based guest paravirt drivers(VMBus).
7573 by the CPU, as it's incompatible with SynIC auto-EOI behavior.
7576 -------------------------
7586 ---------------------------
7593 the POWER9 processor), including in-memory segment tables.
7596 -------------------
7626 -------------------
7640 ----------------------
7645 supported register and address width.
7654 Both registers and addresses are 32-bits wide.
7655 It will only be possible to run 32-bit guest code.
7657 1 MIPS64 or microMIPS64 with access only to 32-bit compatibility segments.
7658 Registers are 64-bits wide, but addresses are 32-bits wide.
7659 64-bit guest code may run but cannot access MIPS64 memory segments.
7660 It will also be possible to run 32-bit guest code.
7663 Both registers and addresses are 64-bits wide.
7664 It will be possible to run 64-bit or 32-bit guest code.
7668 ------------------------
7673 that if userspace creates a VM without an in-kernel interrupt controller, it
7674 will be notified of changes to the output level of in-kernel emulated devices,
7677 updates the vcpu's run->s.regs.device_irq_level field to represent the actual
7683 userspace can always sample the device output level and re-compute the state of
7685 of run->s.regs.device_irq_level on every kvm exit.
7686 The value in run->s.regs.device_irq_level can represent both level and edge
7688 signals will exit to userspace with the bit in run->s.regs.device_irq_level
7691 The field run->s.regs.device_irq_level is available independent of
7692 run->kvm_valid_regs or run->kvm_dirty_regs bits.
7696 and thereby which bits in run->s.regs.device_irq_level can signal values.
7702 KVM_ARM_DEV_EL1_VTIMER - EL1 virtual timer
7703 KVM_ARM_DEV_EL1_PTIMER - EL1 physical timer
7704 KVM_ARM_DEV_PMU - ARM PMU overflow interrupt signal
7711 -----------------------------
7721 --------------------------
7725 This capability enables a newer version of Hyper-V Synthetic interrupt
7731 ----------------------------
7741 -------------------------------
7751 ---------------------
7758 ----------------------
7767 ---------------------
7772 use copy-on-write semantics as well as dirty pages tracking via read-only page
7776 ---------------------
7785 ----------------------------
7789 This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush
7795 ----------------------------------
7810 ----------------------------
7814 This capability indicates that KVM supports paravirtualized Hyper-V IPI send
7819 -----------------------------------
7823 This capability indicates that KVM running on top of Hyper-V hypervisor
7825 hypercalls are handled by Level 0 hypervisor (Hyper-V) bypassing KVM.
7826 Due to the different ABI for hypercall parameters between Hyper-V and
7829 flush hypercalls by Hyper-V) so userspace should disable KVM identification
7830 in CPUID and only exposes Hyper-V identification. In this case, guest
7831 thinks it's running on Hyper-V and only use Hyper-V hypercalls.
7834 -----------------------------
7842 ---------------------------
7853 -----------------------
7859 architecture-specific interfaces. This capability and the architecture-
7866 -------------------------
7876 an 8-byte value consisting of a one-byte Control Program Name Code (CPNC) and
7877 a 7-byte Control Program Version Code (CPVC). The CPNC determines what
7886 -------------------------------
7897 ---------------------------
7911 -------------------------------------
7921 ----------------------------------------------------------
7924 :Parameters: args[0] - size of the dirty log ring
7964 00 -----------> 01 -------------> 1X -------+
7967 +------------------------------------------+
7981 using load-acquire/store-release accessors when available, or any
8009 machine will switch to ring-buffer dirty page tracking and further
8016 Architecture with TSO-like ordering (such as x86) are allowed to
8021 --------------------
8049 The KVM_XEN_HVM_CONFIG_RUNSTATE flag indicates that the runstate-related
8066 -------------------------
8081 IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
8082 present in the "ibm,hypertas-functions" device-tree property.
8092 --------------------
8101 ---------------------------------
8105 When enabled, KVM will disable emulated Hyper-V features provided to the
8106 guest according to the bits Hyper-V CPUID feature leaves. Otherwise, all
8107 currently implmented Hyper-V features are provided unconditionally when
8108 Hyper-V identification is set in the HYPERV_CPUID_INTERFACE (0x40000001)
8112 ---------------------------
8131 ---------------------------
8137 :Returns 0 on success, -EINVAL when arg[0] contains invalid bits
8153 -------------------------------
8163 --------------------------------
8176 -------------------------------------
8182 :Returns: 0 on success, -EPERM if the userspace process does not
8183 have CAP_SYS_BOOT, -EINVAL if args[0] is not 0 or any vCPUs have been
8193 ------------------------------
8214 When getting the Modified Change Topology Report value, the attr->addr
8228 --------
8242 ``KVM_ENABLE_CAP(KVM_CAP_IRQCHIP_SPLIT)`` are used to enable in-kernel emulation of
8249 has enabled in-kernel emulation of the local APIC.