1.. SPDX-License-Identifier: GPL-2.0 2 3=================================================================== 4The Definitive KVM (Kernel-based Virtual Machine) API Documentation 5=================================================================== 6 71. General description 8====================== 9 10The kvm API is centered around different kinds of file descriptors 11and ioctls that can be issued to these file descriptors. An initial 12open("/dev/kvm") obtains a handle to the kvm subsystem; this handle 13can be used to issue system ioctls. A KVM_CREATE_VM ioctl on this 14handle will create a VM file descriptor which can be used to issue VM 15ioctls. A KVM_CREATE_VCPU or KVM_CREATE_DEVICE ioctl on a VM fd will 16create a virtual cpu or device and return a file descriptor pointing to 17the new resource. 18 19In other words, the kvm API is a set of ioctls that are issued to 20different kinds of file descriptor in order to control various aspects of 21a virtual machine. Depending on the file descriptor that accepts them, 22ioctls belong to the following classes: 23 24 - System ioctls: These query and set global attributes which affect the 25 whole kvm subsystem. In addition a system ioctl is used to create 26 virtual machines. 27 28 - VM ioctls: These query and set attributes that affect an entire virtual 29 machine, for example memory layout. In addition a VM ioctl is used to 30 create virtual cpus (vcpus) and devices. 31 32 VM ioctls must be issued from the same process (address space) that was 33 used to create the VM. 34 35 - vcpu ioctls: These query and set attributes that control the operation 36 of a single virtual cpu. 37 38 vcpu ioctls should be issued from the same thread that was used to create 39 the vcpu, except for asynchronous vcpu ioctl that are marked as such in 40 the documentation. Otherwise, the first ioctl after switching threads 41 could see a performance impact. 42 43 - device ioctls: These query and set attributes that control the operation 44 of a single device. 45 46 device ioctls must be issued from the same process (address space) that 47 was used to create the VM. 48 49While most ioctls are specific to one kind of file descriptor, in some 50cases the same ioctl can belong to more than one class. 51 52The KVM API grew over time. For this reason, KVM defines many constants 53of the form ``KVM_CAP_*``, each corresponding to a set of functionality 54provided by one or more ioctls. Availability of these "capabilities" can 55be checked with :ref:`KVM_CHECK_EXTENSION <KVM_CHECK_EXTENSION>`. Some 56capabilities also need to be enabled for VMs or VCPUs where their 57functionality is desired (see :ref:`cap_enable` and :ref:`cap_enable_vm`). 58 59 602. Restrictions 61=============== 62 63In general file descriptors can be migrated among processes by means 64of fork() and the SCM_RIGHTS facility of unix domain socket. These 65kinds of tricks are explicitly not supported by kvm. While they will 66not cause harm to the host, their actual behavior is not guaranteed by 67the API. See "General description" for details on the ioctl usage 68model that is supported by KVM. 69 70It is important to note that although VM ioctls may only be issued from 71the process that created the VM, a VM's lifecycle is associated with its 72file descriptor, not its creator (process). In other words, the VM and 73its resources, *including the associated address space*, are not freed 74until the last reference to the VM's file descriptor has been released. 75For example, if fork() is issued after ioctl(KVM_CREATE_VM), the VM will 76not be freed until both the parent (original) process and its child have 77put their references to the VM's file descriptor. 78 79Because a VM's resources are not freed until the last reference to its 80file descriptor is released, creating additional references to a VM 81via fork(), dup(), etc... without careful consideration is strongly 82discouraged and may have unwanted side effects, e.g. memory allocated 83by and on behalf of the VM's process may not be freed/unaccounted when 84the VM is shut down. 85 86 873. Extensions 88============= 89 90As of Linux 2.6.22, the KVM ABI has been stabilized: no backward 91incompatible change are allowed. However, there is an extension 92facility that allows backward-compatible extensions to the API to be 93queried and used. 94 95The extension mechanism is not based on the Linux version number. 96Instead, kvm defines extension identifiers and a facility to query 97whether a particular extension identifier is available. If it is, a 98set of ioctls is available for application use. 99 100 1014. API description 102================== 103 104This section describes ioctls that can be used to control kvm guests. 105For each ioctl, the following information is provided along with a 106description: 107 108 Capability: 109 which KVM extension provides this ioctl. Can be 'basic', 110 which means that is will be provided by any kernel that supports 111 API version 12 (see :ref:`KVM_GET_API_VERSION <KVM_GET_API_VERSION>`), 112 or a KVM_CAP_xyz constant that can be checked with 113 :ref:`KVM_CHECK_EXTENSION <KVM_CHECK_EXTENSION>`. 114 115 Architectures: 116 which instruction set architectures provide this ioctl. 117 x86 includes both i386 and x86_64. 118 119 Type: 120 system, vm, or vcpu. 121 122 Parameters: 123 what parameters are accepted by the ioctl. 124 125 Returns: 126 the return value. General error numbers (EBADF, ENOMEM, EINVAL) 127 are not detailed, but errors with specific meanings are. 128 129 130.. _KVM_GET_API_VERSION: 131 1324.1 KVM_GET_API_VERSION 133----------------------- 134 135:Capability: basic 136:Architectures: all 137:Type: system ioctl 138:Parameters: none 139:Returns: the constant KVM_API_VERSION (=12) 140 141This identifies the API version as the stable kvm API. It is not 142expected that this number will change. However, Linux 2.6.20 and 1432.6.21 report earlier versions; these are not documented and not 144supported. Applications should refuse to run if KVM_GET_API_VERSION 145returns a value other than 12. If this check passes, all ioctls 146described as 'basic' will be available. 147 148 1494.2 KVM_CREATE_VM 150----------------- 151 152:Capability: basic 153:Architectures: all 154:Type: system ioctl 155:Parameters: machine type identifier (KVM_VM_*) 156:Returns: a VM fd that can be used to control the new virtual machine. 157 158The new VM has no virtual cpus and no memory. 159You probably want to use 0 as machine type. 160 161X86: 162^^^^ 163 164Supported X86 VM types can be queried via KVM_CAP_VM_TYPES. 165 166S390: 167^^^^^ 168 169In order to create user controlled virtual machines on S390, check 170KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as 171privileged user (CAP_SYS_ADMIN). 172 173MIPS: 174^^^^^ 175 176To use hardware assisted virtualization on MIPS (VZ ASE) rather than 177the default trap & emulate implementation (which changes the virtual 178memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the 179flag KVM_VM_MIPS_VZ. 180 181ARM64: 182^^^^^^ 183 184On arm64, the physical address size for a VM (IPA Size limit) is limited 185to 40bits by default. The limit can be configured if the host supports the 186extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use 187KVM_VM_TYPE_ARM_IPA_SIZE(IPA_Bits) to set the size in the machine type 188identifier, where IPA_Bits is the maximum width of any physical 189address used by the VM. The IPA_Bits is encoded in bits[7-0] of the 190machine type identifier. 191 192e.g, to configure a guest to use 48bit physical address size:: 193 194 vm_fd = ioctl(dev_fd, KVM_CREATE_VM, KVM_VM_TYPE_ARM_IPA_SIZE(48)); 195 196The requested size (IPA_Bits) must be: 197 198 == ========================================================= 199 0 Implies default size, 40bits (for backward compatibility) 200 N Implies N bits, where N is a positive integer such that, 201 32 <= N <= Host_IPA_Limit 202 == ========================================================= 203 204Host_IPA_Limit is the maximum possible value for IPA_Bits on the host and 205is dependent on the CPU capability and the kernel configuration. The limit can 206be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of the KVM_CHECK_EXTENSION 207ioctl() at run-time. 208 209Creation of the VM will fail if the requested IPA size (whether it is 210implicit or explicit) is unsupported on the host. 211 212Please note that configuring the IPA size does not affect the capability 213exposed by the guest CPUs in ID_AA64MMFR0_EL1[PARange]. It only affects 214size of the address translated by the stage2 level (guest physical to 215host physical address translations). 216 217 2184.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST 219---------------------------------------------------------- 220 221:Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST 222:Architectures: x86 223:Type: system ioctl 224:Parameters: struct kvm_msr_list (in/out) 225:Returns: 0 on success; -1 on error 226 227Errors: 228 229 ====== ============================================================ 230 EFAULT the msr index list cannot be read from or written to 231 E2BIG the msr index list is too big to fit in the array specified by 232 the user. 233 ====== ============================================================ 234 235:: 236 237 struct kvm_msr_list { 238 __u32 nmsrs; /* number of msrs in entries */ 239 __u32 indices[0]; 240 }; 241 242The user fills in the size of the indices array in nmsrs, and in return 243kvm adjusts nmsrs to reflect the actual number of msrs and fills in the 244indices array with their numbers. 245 246KVM_GET_MSR_INDEX_LIST returns the guest msrs that are supported. The list 247varies by kvm version and host processor, but does not change otherwise. 248 249Note: if kvm indicates supports MCE (KVM_CAP_MCE), then the MCE bank MSRs are 250not returned in the MSR list, as different vcpus can have a different number 251of banks, as set via the KVM_X86_SETUP_MCE ioctl. 252 253KVM_GET_MSR_FEATURE_INDEX_LIST returns the list of MSRs that can be passed 254to the KVM_GET_MSRS system ioctl. This lets userspace probe host capabilities 255and processor features that are exposed via MSRs (e.g., VMX capabilities). 256This list also varies by kvm version and host processor, but does not change 257otherwise. 258 259 260.. _KVM_CHECK_EXTENSION: 261 2624.4 KVM_CHECK_EXTENSION 263----------------------- 264 265:Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl 266:Architectures: all 267:Type: system ioctl, vm ioctl 268:Parameters: extension identifier (KVM_CAP_*) 269:Returns: 0 if unsupported; 1 (or some other positive integer) if supported 270 271The API allows the application to query about extensions to the core 272kvm API. Userspace passes an extension identifier (an integer) and 273receives an integer that describes the extension availability. 274Generally 0 means no and 1 means yes, but some extensions may report 275additional information in the integer return value. 276 277Based on their initialization different VMs may have different capabilities. 278It is thus encouraged to use the vm ioctl to query for capabilities (available 279with KVM_CAP_CHECK_EXTENSION_VM on the vm fd) 280 2814.5 KVM_GET_VCPU_MMAP_SIZE 282-------------------------- 283 284:Capability: basic 285:Architectures: all 286:Type: system ioctl 287:Parameters: none 288:Returns: size of vcpu mmap area, in bytes 289 290The KVM_RUN ioctl (cf.) communicates with userspace via a shared 291memory region. This ioctl returns the size of that region. See the 292KVM_RUN documentation for details. 293 294Besides the size of the KVM_RUN communication region, other areas of 295the VCPU file descriptor can be mmap-ed, including: 296 297- if KVM_CAP_COALESCED_MMIO is available, a page at 298 KVM_COALESCED_MMIO_PAGE_OFFSET * PAGE_SIZE; for historical reasons, 299 this page is included in the result of KVM_GET_VCPU_MMAP_SIZE. 300 KVM_CAP_COALESCED_MMIO is not documented yet. 301 302- if KVM_CAP_DIRTY_LOG_RING is available, a number of pages at 303 KVM_DIRTY_LOG_PAGE_OFFSET * PAGE_SIZE. For more information on 304 KVM_CAP_DIRTY_LOG_RING, see :ref:`KVM_CAP_DIRTY_LOG_RING`. 305 306 3074.7 KVM_CREATE_VCPU 308------------------- 309 310:Capability: basic 311:Architectures: all 312:Type: vm ioctl 313:Parameters: vcpu id (apic id on x86) 314:Returns: vcpu fd on success, -1 on error 315 316This API adds a vcpu to a virtual machine. No more than max_vcpus may be added. 317The vcpu id is an integer in the range [0, max_vcpu_id). 318 319The recommended max_vcpus value can be retrieved using the KVM_CAP_NR_VCPUS of 320the KVM_CHECK_EXTENSION ioctl() at run-time. 321The maximum possible value for max_vcpus can be retrieved using the 322KVM_CAP_MAX_VCPUS of the KVM_CHECK_EXTENSION ioctl() at run-time. 323 324If the KVM_CAP_NR_VCPUS does not exist, you should assume that max_vcpus is 4 325cpus max. 326If the KVM_CAP_MAX_VCPUS does not exist, you should assume that max_vcpus is 327same as the value returned from KVM_CAP_NR_VCPUS. 328 329The maximum possible value for max_vcpu_id can be retrieved using the 330KVM_CAP_MAX_VCPU_ID of the KVM_CHECK_EXTENSION ioctl() at run-time. 331 332If the KVM_CAP_MAX_VCPU_ID does not exist, you should assume that max_vcpu_id 333is the same as the value returned from KVM_CAP_MAX_VCPUS. 334 335On powerpc using book3s_hv mode, the vcpus are mapped onto virtual 336threads in one or more virtual CPU cores. (This is because the 337hardware requires all the hardware threads in a CPU core to be in the 338same partition.) The KVM_CAP_PPC_SMT capability indicates the number 339of vcpus per virtual core (vcore). The vcore id is obtained by 340dividing the vcpu id by the number of vcpus per vcore. The vcpus in a 341given vcore will always be in the same physical core as each other 342(though that might be a different physical core from time to time). 343Userspace can control the threading (SMT) mode of the guest by its 344allocation of vcpu ids. For example, if userspace wants 345single-threaded guest vcpus, it should make all vcpu ids be a multiple 346of the number of vcpus per vcore. 347 348For virtual cpus that have been created with S390 user controlled virtual 349machines, the resulting vcpu fd can be memory mapped at page offset 350KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of the virtual 351cpu's hardware control block. 352 353 3544.8 KVM_GET_DIRTY_LOG 355--------------------- 356 357:Capability: basic 358:Architectures: all 359:Type: vm ioctl 360:Parameters: struct kvm_dirty_log (in/out) 361:Returns: 0 on success, -1 on error 362 363:: 364 365 /* for KVM_GET_DIRTY_LOG */ 366 struct kvm_dirty_log { 367 __u32 slot; 368 __u32 padding; 369 union { 370 void __user *dirty_bitmap; /* one bit per page */ 371 __u64 padding; 372 }; 373 }; 374 375Given a memory slot, return a bitmap containing any pages dirtied 376since the last call to this ioctl. Bit 0 is the first page in the 377memory slot. Ensure the entire structure is cleared to avoid padding 378issues. 379 380If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of slot field specifies 381the address space for which you want to return the dirty bitmap. See 382KVM_SET_USER_MEMORY_REGION for details on the usage of slot field. 383 384The bits in the dirty bitmap are cleared before the ioctl returns, unless 385KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is enabled. For more information, 386see the description of the capability. 387 388Note that the Xen shared_info page, if configured, shall always be assumed 389to be dirty. KVM will not explicitly mark it such. 390 391 3924.10 KVM_RUN 393------------ 394 395:Capability: basic 396:Architectures: all 397:Type: vcpu ioctl 398:Parameters: none 399:Returns: 0 on success, -1 on error 400 401Errors: 402 403 ======= ============================================================== 404 EINTR an unmasked signal is pending 405 ENOEXEC the vcpu hasn't been initialized or the guest tried to execute 406 instructions from device memory (arm64) 407 ENOSYS data abort outside memslots with no syndrome info and 408 KVM_CAP_ARM_NISV_TO_USER not enabled (arm64) 409 EPERM SVE feature set but not finalized (arm64) 410 ======= ============================================================== 411 412This ioctl is used to run a guest virtual cpu. While there are no 413explicit parameters, there is an implicit parameter block that can be 414obtained by mmap()ing the vcpu fd at offset 0, with the size given by 415KVM_GET_VCPU_MMAP_SIZE. The parameter block is formatted as a 'struct 416kvm_run' (see below). 417 418 4194.11 KVM_GET_REGS 420----------------- 421 422:Capability: basic 423:Architectures: all except arm64 424:Type: vcpu ioctl 425:Parameters: struct kvm_regs (out) 426:Returns: 0 on success, -1 on error 427 428Reads the general purpose registers from the vcpu. 429 430:: 431 432 /* x86 */ 433 struct kvm_regs { 434 /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ 435 __u64 rax, rbx, rcx, rdx; 436 __u64 rsi, rdi, rsp, rbp; 437 __u64 r8, r9, r10, r11; 438 __u64 r12, r13, r14, r15; 439 __u64 rip, rflags; 440 }; 441 442 /* mips */ 443 struct kvm_regs { 444 /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ 445 __u64 gpr[32]; 446 __u64 hi; 447 __u64 lo; 448 __u64 pc; 449 }; 450 451 /* LoongArch */ 452 struct kvm_regs { 453 /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ 454 unsigned long gpr[32]; 455 unsigned long pc; 456 }; 457 458 4594.12 KVM_SET_REGS 460----------------- 461 462:Capability: basic 463:Architectures: all except arm64 464:Type: vcpu ioctl 465:Parameters: struct kvm_regs (in) 466:Returns: 0 on success, -1 on error 467 468Writes the general purpose registers into the vcpu. 469 470See KVM_GET_REGS for the data structure. 471 472 4734.13 KVM_GET_SREGS 474------------------ 475 476:Capability: basic 477:Architectures: x86, ppc 478:Type: vcpu ioctl 479:Parameters: struct kvm_sregs (out) 480:Returns: 0 on success, -1 on error 481 482Reads special registers from the vcpu. 483 484:: 485 486 /* x86 */ 487 struct kvm_sregs { 488 struct kvm_segment cs, ds, es, fs, gs, ss; 489 struct kvm_segment tr, ldt; 490 struct kvm_dtable gdt, idt; 491 __u64 cr0, cr2, cr3, cr4, cr8; 492 __u64 efer; 493 __u64 apic_base; 494 __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64]; 495 }; 496 497 /* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */ 498 499interrupt_bitmap is a bitmap of pending external interrupts. At most 500one bit may be set. This interrupt has been acknowledged by the APIC 501but not yet injected into the cpu core. 502 503 5044.14 KVM_SET_SREGS 505------------------ 506 507:Capability: basic 508:Architectures: x86, ppc 509:Type: vcpu ioctl 510:Parameters: struct kvm_sregs (in) 511:Returns: 0 on success, -1 on error 512 513Writes special registers into the vcpu. See KVM_GET_SREGS for the 514data structures. 515 516 5174.15 KVM_TRANSLATE 518------------------ 519 520:Capability: basic 521:Architectures: x86 522:Type: vcpu ioctl 523:Parameters: struct kvm_translation (in/out) 524:Returns: 0 on success, -1 on error 525 526Translates a virtual address according to the vcpu's current address 527translation mode. 528 529:: 530 531 struct kvm_translation { 532 /* in */ 533 __u64 linear_address; 534 535 /* out */ 536 __u64 physical_address; 537 __u8 valid; 538 __u8 writeable; 539 __u8 usermode; 540 __u8 pad[5]; 541 }; 542 543 5444.16 KVM_INTERRUPT 545------------------ 546 547:Capability: basic 548:Architectures: x86, ppc, mips, riscv, loongarch 549:Type: vcpu ioctl 550:Parameters: struct kvm_interrupt (in) 551:Returns: 0 on success, negative on failure. 552 553Queues a hardware interrupt vector to be injected. 554 555:: 556 557 /* for KVM_INTERRUPT */ 558 struct kvm_interrupt { 559 /* in */ 560 __u32 irq; 561 }; 562 563X86: 564^^^^ 565 566:Returns: 567 568 ========= =================================== 569 0 on success, 570 -EEXIST if an interrupt is already enqueued 571 -EINVAL the irq number is invalid 572 -ENXIO if the PIC is in the kernel 573 -EFAULT if the pointer is invalid 574 ========= =================================== 575 576Note 'irq' is an interrupt vector, not an interrupt pin or line. This 577ioctl is useful if the in-kernel PIC is not used. 578 579PPC: 580^^^^ 581 582Queues an external interrupt to be injected. This ioctl is overloaded 583with 3 different irq values: 584 585a) KVM_INTERRUPT_SET 586 587 This injects an edge type external interrupt into the guest once it's ready 588 to receive interrupts. When injected, the interrupt is done. 589 590b) KVM_INTERRUPT_UNSET 591 592 This unsets any pending interrupt. 593 594 Only available with KVM_CAP_PPC_UNSET_IRQ. 595 596c) KVM_INTERRUPT_SET_LEVEL 597 598 This injects a level type external interrupt into the guest context. The 599 interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET 600 is triggered. 601 602 Only available with KVM_CAP_PPC_IRQ_LEVEL. 603 604Note that any value for 'irq' other than the ones stated above is invalid 605and incurs unexpected behavior. 606 607This is an asynchronous vcpu ioctl and can be invoked from any thread. 608 609MIPS: 610^^^^^ 611 612Queues an external interrupt to be injected into the virtual CPU. A negative 613interrupt number dequeues the interrupt. 614 615This is an asynchronous vcpu ioctl and can be invoked from any thread. 616 617RISC-V: 618^^^^^^^ 619 620Queues an external interrupt to be injected into the virtual CPU. This ioctl 621is overloaded with 2 different irq values: 622 623a) KVM_INTERRUPT_SET 624 625 This sets external interrupt for a virtual CPU and it will receive 626 once it is ready. 627 628b) KVM_INTERRUPT_UNSET 629 630 This clears pending external interrupt for a virtual CPU. 631 632This is an asynchronous vcpu ioctl and can be invoked from any thread. 633 634LOONGARCH: 635^^^^^^^^^^ 636 637Queues an external interrupt to be injected into the virtual CPU. A negative 638interrupt number dequeues the interrupt. 639 640This is an asynchronous vcpu ioctl and can be invoked from any thread. 641 642 6434.18 KVM_GET_MSRS 644----------------- 645 646:Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system) 647:Architectures: x86 648:Type: system ioctl, vcpu ioctl 649:Parameters: struct kvm_msrs (in/out) 650:Returns: number of msrs successfully returned; 651 -1 on error 652 653When used as a system ioctl: 654Reads the values of MSR-based features that are available for the VM. This 655is similar to KVM_GET_SUPPORTED_CPUID, but it returns MSR indices and values. 656The list of msr-based features can be obtained using KVM_GET_MSR_FEATURE_INDEX_LIST 657in a system ioctl. 658 659When used as a vcpu ioctl: 660Reads model-specific registers from the vcpu. Supported msr indices can 661be obtained using KVM_GET_MSR_INDEX_LIST in a system ioctl. 662 663:: 664 665 struct kvm_msrs { 666 __u32 nmsrs; /* number of msrs in entries */ 667 __u32 pad; 668 669 struct kvm_msr_entry entries[0]; 670 }; 671 672 struct kvm_msr_entry { 673 __u32 index; 674 __u32 reserved; 675 __u64 data; 676 }; 677 678Application code should set the 'nmsrs' member (which indicates the 679size of the entries array) and the 'index' member of each array entry. 680kvm will fill in the 'data' member. 681 682 6834.19 KVM_SET_MSRS 684----------------- 685 686:Capability: basic 687:Architectures: x86 688:Type: vcpu ioctl 689:Parameters: struct kvm_msrs (in) 690:Returns: number of msrs successfully set (see below), -1 on error 691 692Writes model-specific registers to the vcpu. See KVM_GET_MSRS for the 693data structures. 694 695Application code should set the 'nmsrs' member (which indicates the 696size of the entries array), and the 'index' and 'data' members of each 697array entry. 698 699It tries to set the MSRs in array entries[] one by one. If setting an MSR 700fails, e.g., due to setting reserved bits, the MSR isn't supported/emulated 701by KVM, etc..., it stops processing the MSR list and returns the number of 702MSRs that have been set successfully. 703 704 7054.20 KVM_SET_CPUID 706------------------ 707 708:Capability: basic 709:Architectures: x86 710:Type: vcpu ioctl 711:Parameters: struct kvm_cpuid (in) 712:Returns: 0 on success, -1 on error 713 714Defines the vcpu responses to the cpuid instruction. Applications 715should use the KVM_SET_CPUID2 ioctl if available. 716 717Caveat emptor: 718 - If this IOCTL fails, KVM gives no guarantees that previous valid CPUID 719 configuration (if there is) is not corrupted. Userspace can get a copy 720 of the resulting CPUID configuration through KVM_GET_CPUID2 in case. 721 - Using KVM_SET_CPUID{,2} after KVM_RUN, i.e. changing the guest vCPU model 722 after running the guest, may cause guest instability. 723 - Using heterogeneous CPUID configurations, modulo APIC IDs, topology, etc... 724 may cause guest instability. 725 726:: 727 728 struct kvm_cpuid_entry { 729 __u32 function; 730 __u32 eax; 731 __u32 ebx; 732 __u32 ecx; 733 __u32 edx; 734 __u32 padding; 735 }; 736 737 /* for KVM_SET_CPUID */ 738 struct kvm_cpuid { 739 __u32 nent; 740 __u32 padding; 741 struct kvm_cpuid_entry entries[0]; 742 }; 743 744 7454.21 KVM_SET_SIGNAL_MASK 746------------------------ 747 748:Capability: basic 749:Architectures: all 750:Type: vcpu ioctl 751:Parameters: struct kvm_signal_mask (in) 752:Returns: 0 on success, -1 on error 753 754Defines which signals are blocked during execution of KVM_RUN. This 755signal mask temporarily overrides the threads signal mask. Any 756unblocked signal received (except SIGKILL and SIGSTOP, which retain 757their traditional behaviour) will cause KVM_RUN to return with -EINTR. 758 759Note the signal will only be delivered if not blocked by the original 760signal mask. 761 762:: 763 764 /* for KVM_SET_SIGNAL_MASK */ 765 struct kvm_signal_mask { 766 __u32 len; 767 __u8 sigset[0]; 768 }; 769 770 7714.22 KVM_GET_FPU 772---------------- 773 774:Capability: basic 775:Architectures: x86, loongarch 776:Type: vcpu ioctl 777:Parameters: struct kvm_fpu (out) 778:Returns: 0 on success, -1 on error 779 780Reads the floating point state from the vcpu. 781 782:: 783 784 /* x86: for KVM_GET_FPU and KVM_SET_FPU */ 785 struct kvm_fpu { 786 __u8 fpr[8][16]; 787 __u16 fcw; 788 __u16 fsw; 789 __u8 ftwx; /* in fxsave format */ 790 __u8 pad1; 791 __u16 last_opcode; 792 __u64 last_ip; 793 __u64 last_dp; 794 __u8 xmm[16][16]; 795 __u32 mxcsr; 796 __u32 pad2; 797 }; 798 799 /* LoongArch: for KVM_GET_FPU and KVM_SET_FPU */ 800 struct kvm_fpu { 801 __u32 fcsr; 802 __u64 fcc; 803 struct kvm_fpureg { 804 __u64 val64[4]; 805 }fpr[32]; 806 }; 807 808 8094.23 KVM_SET_FPU 810---------------- 811 812:Capability: basic 813:Architectures: x86, loongarch 814:Type: vcpu ioctl 815:Parameters: struct kvm_fpu (in) 816:Returns: 0 on success, -1 on error 817 818Writes the floating point state to the vcpu. 819 820:: 821 822 /* x86: for KVM_GET_FPU and KVM_SET_FPU */ 823 struct kvm_fpu { 824 __u8 fpr[8][16]; 825 __u16 fcw; 826 __u16 fsw; 827 __u8 ftwx; /* in fxsave format */ 828 __u8 pad1; 829 __u16 last_opcode; 830 __u64 last_ip; 831 __u64 last_dp; 832 __u8 xmm[16][16]; 833 __u32 mxcsr; 834 __u32 pad2; 835 }; 836 837 /* LoongArch: for KVM_GET_FPU and KVM_SET_FPU */ 838 struct kvm_fpu { 839 __u32 fcsr; 840 __u64 fcc; 841 struct kvm_fpureg { 842 __u64 val64[4]; 843 }fpr[32]; 844 }; 845 846 8474.24 KVM_CREATE_IRQCHIP 848----------------------- 849 850:Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390) 851:Architectures: x86, arm64, s390 852:Type: vm ioctl 853:Parameters: none 854:Returns: 0 on success, -1 on error 855 856Creates an interrupt controller model in the kernel. 857On x86, creates a virtual ioapic, a virtual PIC (two PICs, nested), and sets up 858future vcpus to have a local APIC. IRQ routing for GSIs 0-15 is set to both 859PIC and IOAPIC; GSI 16-23 only go to the IOAPIC. 860On arm64, a GICv2 is created. Any other GIC versions require the usage of 861KVM_CREATE_DEVICE, which also supports creating a GICv2. Using 862KVM_CREATE_DEVICE is preferred over KVM_CREATE_IRQCHIP for GICv2. 863On s390, a dummy irq routing table is created. 864 865Note that on s390 the KVM_CAP_S390_IRQCHIP vm capability needs to be enabled 866before KVM_CREATE_IRQCHIP can be used. 867 868 8694.25 KVM_IRQ_LINE 870----------------- 871 872:Capability: KVM_CAP_IRQCHIP 873:Architectures: x86, arm64 874:Type: vm ioctl 875:Parameters: struct kvm_irq_level 876:Returns: 0 on success, -1 on error 877 878Sets the level of a GSI input to the interrupt controller model in the kernel. 879On some architectures it is required that an interrupt controller model has 880been previously created with KVM_CREATE_IRQCHIP. Note that edge-triggered 881interrupts require the level to be set to 1 and then back to 0. 882 883On real hardware, interrupt pins can be active-low or active-high. This 884does not matter for the level field of struct kvm_irq_level: 1 always 885means active (asserted), 0 means inactive (deasserted). 886 887x86 allows the operating system to program the interrupt polarity 888(active-low/active-high) for level-triggered interrupts, and KVM used 889to consider the polarity. However, due to bitrot in the handling of 890active-low interrupts, the above convention is now valid on x86 too. 891This is signaled by KVM_CAP_X86_IOAPIC_POLARITY_IGNORED. Userspace 892should not present interrupts to the guest as active-low unless this 893capability is present (or unless it is not using the in-kernel irqchip, 894of course). 895 896 897arm64 can signal an interrupt either at the CPU level, or at the 898in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to 899use PPIs designated for specific cpus. The irq field is interpreted 900like this:: 901 902 bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 | 903 field: | vcpu2_index | irq_type | vcpu_index | irq_id | 904 905The irq_type field has the following values: 906 907- KVM_ARM_IRQ_TYPE_CPU: 908 out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ 909- KVM_ARM_IRQ_TYPE_SPI: 910 in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.) 911 (the vcpu_index field is ignored) 912- KVM_ARM_IRQ_TYPE_PPI: 913 in-kernel GIC: PPI, irq_id between 16 and 31 (incl.) 914 915(The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs) 916 917In both cases, level is used to assert/deassert the line. 918 919When KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 is supported, the target vcpu is 920identified as (256 * vcpu2_index + vcpu_index). Otherwise, vcpu2_index 921must be zero. 922 923Note that on arm64, the KVM_CAP_IRQCHIP capability only conditions 924injection of interrupts for the in-kernel irqchip. KVM_IRQ_LINE can always 925be used for a userspace interrupt controller. 926 927:: 928 929 struct kvm_irq_level { 930 union { 931 __u32 irq; /* GSI */ 932 __s32 status; /* not used for KVM_IRQ_LEVEL */ 933 }; 934 __u32 level; /* 0 or 1 */ 935 }; 936 937 9384.26 KVM_GET_IRQCHIP 939-------------------- 940 941:Capability: KVM_CAP_IRQCHIP 942:Architectures: x86 943:Type: vm ioctl 944:Parameters: struct kvm_irqchip (in/out) 945:Returns: 0 on success, -1 on error 946 947Reads the state of a kernel interrupt controller created with 948KVM_CREATE_IRQCHIP into a buffer provided by the caller. 949 950:: 951 952 struct kvm_irqchip { 953 __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */ 954 __u32 pad; 955 union { 956 char dummy[512]; /* reserving space */ 957 struct kvm_pic_state pic; 958 struct kvm_ioapic_state ioapic; 959 } chip; 960 }; 961 962 9634.27 KVM_SET_IRQCHIP 964-------------------- 965 966:Capability: KVM_CAP_IRQCHIP 967:Architectures: x86 968:Type: vm ioctl 969:Parameters: struct kvm_irqchip (in) 970:Returns: 0 on success, -1 on error 971 972Sets the state of a kernel interrupt controller created with 973KVM_CREATE_IRQCHIP from a buffer provided by the caller. 974 975:: 976 977 struct kvm_irqchip { 978 __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */ 979 __u32 pad; 980 union { 981 char dummy[512]; /* reserving space */ 982 struct kvm_pic_state pic; 983 struct kvm_ioapic_state ioapic; 984 } chip; 985 }; 986 987 9884.28 KVM_XEN_HVM_CONFIG 989----------------------- 990 991:Capability: KVM_CAP_XEN_HVM 992:Architectures: x86 993:Type: vm ioctl 994:Parameters: struct kvm_xen_hvm_config (in) 995:Returns: 0 on success, -1 on error 996 997Sets the MSR that the Xen HVM guest uses to initialize its hypercall 998page, and provides the starting address and size of the hypercall 999blobs in userspace. When the guest writes the MSR, kvm copies one 1000page of a blob (32- or 64-bit, depending on the vcpu mode) to guest 1001memory. 1002 1003The MSR index must be in the range [0x40000000, 0x4fffffff], i.e. must reside 1004in the range that is unofficially reserved for use by hypervisors. The min/max 1005values are enumerated via KVM_XEN_MSR_MIN_INDEX and KVM_XEN_MSR_MAX_INDEX. 1006 1007:: 1008 1009 struct kvm_xen_hvm_config { 1010 __u32 flags; 1011 __u32 msr; 1012 __u64 blob_addr_32; 1013 __u64 blob_addr_64; 1014 __u8 blob_size_32; 1015 __u8 blob_size_64; 1016 __u8 pad2[30]; 1017 }; 1018 1019If certain flags are returned from the KVM_CAP_XEN_HVM check, they may 1020be set in the flags field of this ioctl: 1021 1022The KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL flag requests KVM to generate 1023the contents of the hypercall page automatically; hypercalls will be 1024intercepted and passed to userspace through KVM_EXIT_XEN. In this 1025case, all of the blob size and address fields must be zero. 1026 1027The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indicates to KVM that userspace 1028will always use the KVM_XEN_HVM_EVTCHN_SEND ioctl to deliver event 1029channel interrupts rather than manipulating the guest's shared_info 1030structures directly. This, in turn, may allow KVM to enable features 1031such as intercepting the SCHEDOP_poll hypercall to accelerate PV 1032spinlock operation for the guest. Userspace may still use the ioctl 1033to deliver events if it was advertised, even if userspace does not 1034send this indication that it will always do so 1035 1036No other flags are currently valid in the struct kvm_xen_hvm_config. 1037 10384.29 KVM_GET_CLOCK 1039------------------ 1040 1041:Capability: KVM_CAP_ADJUST_CLOCK 1042:Architectures: x86 1043:Type: vm ioctl 1044:Parameters: struct kvm_clock_data (out) 1045:Returns: 0 on success, -1 on error 1046 1047Gets the current timestamp of kvmclock as seen by the current guest. In 1048conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios 1049such as migration. 1050 1051When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the 1052set of bits that KVM can return in struct kvm_clock_data's flag member. 1053 1054The following flags are defined: 1055 1056KVM_CLOCK_TSC_STABLE 1057 If set, the returned value is the exact kvmclock 1058 value seen by all VCPUs at the instant when KVM_GET_CLOCK was called. 1059 If clear, the returned value is simply CLOCK_MONOTONIC plus a constant 1060 offset; the offset can be modified with KVM_SET_CLOCK. KVM will try 1061 to make all VCPUs follow this clock, but the exact value read by each 1062 VCPU could differ, because the host TSC is not stable. 1063 1064KVM_CLOCK_REALTIME 1065 If set, the `realtime` field in the kvm_clock_data 1066 structure is populated with the value of the host's real time 1067 clocksource at the instant when KVM_GET_CLOCK was called. If clear, 1068 the `realtime` field does not contain a value. 1069 1070KVM_CLOCK_HOST_TSC 1071 If set, the `host_tsc` field in the kvm_clock_data 1072 structure is populated with the value of the host's timestamp counter (TSC) 1073 at the instant when KVM_GET_CLOCK was called. If clear, the `host_tsc` field 1074 does not contain a value. 1075 1076:: 1077 1078 struct kvm_clock_data { 1079 __u64 clock; /* kvmclock current value */ 1080 __u32 flags; 1081 __u32 pad0; 1082 __u64 realtime; 1083 __u64 host_tsc; 1084 __u32 pad[4]; 1085 }; 1086 1087 10884.30 KVM_SET_CLOCK 1089------------------ 1090 1091:Capability: KVM_CAP_ADJUST_CLOCK 1092:Architectures: x86 1093:Type: vm ioctl 1094:Parameters: struct kvm_clock_data (in) 1095:Returns: 0 on success, -1 on error 1096 1097Sets the current timestamp of kvmclock to the value specified in its parameter. 1098In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios 1099such as migration. 1100 1101The following flags can be passed: 1102 1103KVM_CLOCK_REALTIME 1104 If set, KVM will compare the value of the `realtime` field 1105 with the value of the host's real time clocksource at the instant when 1106 KVM_SET_CLOCK was called. The difference in elapsed time is added to the final 1107 kvmclock value that will be provided to guests. 1108 1109Other flags returned by ``KVM_GET_CLOCK`` are accepted but ignored. 1110 1111:: 1112 1113 struct kvm_clock_data { 1114 __u64 clock; /* kvmclock current value */ 1115 __u32 flags; 1116 __u32 pad0; 1117 __u64 realtime; 1118 __u64 host_tsc; 1119 __u32 pad[4]; 1120 }; 1121 1122 11234.31 KVM_GET_VCPU_EVENTS 1124------------------------ 1125 1126:Capability: KVM_CAP_VCPU_EVENTS 1127:Extended by: KVM_CAP_INTR_SHADOW 1128:Architectures: x86, arm64 1129:Type: vcpu ioctl 1130:Parameters: struct kvm_vcpu_events (out) 1131:Returns: 0 on success, -1 on error 1132 1133X86: 1134^^^^ 1135 1136Gets currently pending exceptions, interrupts, and NMIs as well as related 1137states of the vcpu. 1138 1139:: 1140 1141 struct kvm_vcpu_events { 1142 struct { 1143 __u8 injected; 1144 __u8 nr; 1145 __u8 has_error_code; 1146 __u8 pending; 1147 __u32 error_code; 1148 } exception; 1149 struct { 1150 __u8 injected; 1151 __u8 nr; 1152 __u8 soft; 1153 __u8 shadow; 1154 } interrupt; 1155 struct { 1156 __u8 injected; 1157 __u8 pending; 1158 __u8 masked; 1159 __u8 pad; 1160 } nmi; 1161 __u32 sipi_vector; 1162 __u32 flags; 1163 struct { 1164 __u8 smm; 1165 __u8 pending; 1166 __u8 smm_inside_nmi; 1167 __u8 latched_init; 1168 } smi; 1169 __u8 reserved[27]; 1170 __u8 exception_has_payload; 1171 __u64 exception_payload; 1172 }; 1173 1174The following bits are defined in the flags field: 1175 1176- KVM_VCPUEVENT_VALID_SHADOW may be set to signal that 1177 interrupt.shadow contains a valid state. 1178 1179- KVM_VCPUEVENT_VALID_SMM may be set to signal that smi contains a 1180 valid state. 1181 1182- KVM_VCPUEVENT_VALID_PAYLOAD may be set to signal that the 1183 exception_has_payload, exception_payload, and exception.pending 1184 fields contain a valid state. This bit will be set whenever 1185 KVM_CAP_EXCEPTION_PAYLOAD is enabled. 1186 1187- KVM_VCPUEVENT_VALID_TRIPLE_FAULT may be set to signal that the 1188 triple_fault_pending field contains a valid state. This bit will 1189 be set whenever KVM_CAP_X86_TRIPLE_FAULT_EVENT is enabled. 1190 1191ARM64: 1192^^^^^^ 1193 1194If the guest accesses a device that is being emulated by the host kernel in 1195such a way that a real device would generate a physical SError, KVM may make 1196a virtual SError pending for that VCPU. This system error interrupt remains 1197pending until the guest takes the exception by unmasking PSTATE.A. 1198 1199Running the VCPU may cause it to take a pending SError, or make an access that 1200causes an SError to become pending. The event's description is only valid while 1201the VPCU is not running. 1202 1203This API provides a way to read and write the pending 'event' state that is not 1204visible to the guest. To save, restore or migrate a VCPU the struct representing 1205the state can be read then written using this GET/SET API, along with the other 1206guest-visible registers. It is not possible to 'cancel' an SError that has been 1207made pending. 1208 1209A device being emulated in user-space may also wish to generate an SError. To do 1210this the events structure can be populated by user-space. The current state 1211should be read first, to ensure no existing SError is pending. If an existing 1212SError is pending, the architecture's 'Multiple SError interrupts' rules should 1213be followed. (2.5.3 of DDI0587.a "ARM Reliability, Availability, and 1214Serviceability (RAS) Specification"). 1215 1216SError exceptions always have an ESR value. Some CPUs have the ability to 1217specify what the virtual SError's ESR value should be. These systems will 1218advertise KVM_CAP_ARM_INJECT_SERROR_ESR. In this case exception.has_esr will 1219always have a non-zero value when read, and the agent making an SError pending 1220should specify the ISS field in the lower 24 bits of exception.serror_esr. If 1221the system supports KVM_CAP_ARM_INJECT_SERROR_ESR, but user-space sets the events 1222with exception.has_esr as zero, KVM will choose an ESR. 1223 1224Specifying exception.has_esr on a system that does not support it will return 1225-EINVAL. Setting anything other than the lower 24bits of exception.serror_esr 1226will return -EINVAL. 1227 1228It is not possible to read back a pending external abort (injected via 1229KVM_SET_VCPU_EVENTS or otherwise) because such an exception is always delivered 1230directly to the virtual CPU). 1231 1232:: 1233 1234 struct kvm_vcpu_events { 1235 struct { 1236 __u8 serror_pending; 1237 __u8 serror_has_esr; 1238 __u8 ext_dabt_pending; 1239 /* Align it to 8 bytes */ 1240 __u8 pad[5]; 1241 __u64 serror_esr; 1242 } exception; 1243 __u32 reserved[12]; 1244 }; 1245 12464.32 KVM_SET_VCPU_EVENTS 1247------------------------ 1248 1249:Capability: KVM_CAP_VCPU_EVENTS 1250:Extended by: KVM_CAP_INTR_SHADOW 1251:Architectures: x86, arm64 1252:Type: vcpu ioctl 1253:Parameters: struct kvm_vcpu_events (in) 1254:Returns: 0 on success, -1 on error 1255 1256X86: 1257^^^^ 1258 1259Set pending exceptions, interrupts, and NMIs as well as related states of the 1260vcpu. 1261 1262See KVM_GET_VCPU_EVENTS for the data structure. 1263 1264Fields that may be modified asynchronously by running VCPUs can be excluded 1265from the update. These fields are nmi.pending, sipi_vector, smi.smm, 1266smi.pending. Keep the corresponding bits in the flags field cleared to 1267suppress overwriting the current in-kernel state. The bits are: 1268 1269=============================== ================================== 1270KVM_VCPUEVENT_VALID_NMI_PENDING transfer nmi.pending to the kernel 1271KVM_VCPUEVENT_VALID_SIPI_VECTOR transfer sipi_vector 1272KVM_VCPUEVENT_VALID_SMM transfer the smi sub-struct. 1273=============================== ================================== 1274 1275If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in 1276the flags field to signal that interrupt.shadow contains a valid state and 1277shall be written into the VCPU. 1278 1279KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available. 1280 1281If KVM_CAP_EXCEPTION_PAYLOAD is enabled, KVM_VCPUEVENT_VALID_PAYLOAD 1282can be set in the flags field to signal that the 1283exception_has_payload, exception_payload, and exception.pending fields 1284contain a valid state and shall be written into the VCPU. 1285 1286If KVM_CAP_X86_TRIPLE_FAULT_EVENT is enabled, KVM_VCPUEVENT_VALID_TRIPLE_FAULT 1287can be set in flags field to signal that the triple_fault field contains 1288a valid state and shall be written into the VCPU. 1289 1290ARM64: 1291^^^^^^ 1292 1293User space may need to inject several types of events to the guest. 1294 1295Set the pending SError exception state for this VCPU. It is not possible to 1296'cancel' an Serror that has been made pending. 1297 1298If the guest performed an access to I/O memory which could not be handled by 1299userspace, for example because of missing instruction syndrome decode 1300information or because there is no device mapped at the accessed IPA, then 1301userspace can ask the kernel to inject an external abort using the address 1302from the exiting fault on the VCPU. It is a programming error to set 1303ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO or 1304KVM_EXIT_ARM_NISV. This feature is only available if the system supports 1305KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which provides commonality in 1306how userspace reports accesses for the above cases to guests, across different 1307userspace implementations. Nevertheless, userspace can still emulate all Arm 1308exceptions by manipulating individual registers using the KVM_SET_ONE_REG API. 1309 1310See KVM_GET_VCPU_EVENTS for the data structure. 1311 1312 13134.33 KVM_GET_DEBUGREGS 1314---------------------- 1315 1316:Capability: KVM_CAP_DEBUGREGS 1317:Architectures: x86 1318:Type: vcpu ioctl 1319:Parameters: struct kvm_debugregs (out) 1320:Returns: 0 on success, -1 on error 1321 1322Reads debug registers from the vcpu. 1323 1324:: 1325 1326 struct kvm_debugregs { 1327 __u64 db[4]; 1328 __u64 dr6; 1329 __u64 dr7; 1330 __u64 flags; 1331 __u64 reserved[9]; 1332 }; 1333 1334 13354.34 KVM_SET_DEBUGREGS 1336---------------------- 1337 1338:Capability: KVM_CAP_DEBUGREGS 1339:Architectures: x86 1340:Type: vcpu ioctl 1341:Parameters: struct kvm_debugregs (in) 1342:Returns: 0 on success, -1 on error 1343 1344Writes debug registers into the vcpu. 1345 1346See KVM_GET_DEBUGREGS for the data structure. The flags field is unused 1347yet and must be cleared on entry. 1348 1349 13504.35 KVM_SET_USER_MEMORY_REGION 1351------------------------------- 1352 1353:Capability: KVM_CAP_USER_MEMORY 1354:Architectures: all 1355:Type: vm ioctl 1356:Parameters: struct kvm_userspace_memory_region (in) 1357:Returns: 0 on success, -1 on error 1358 1359:: 1360 1361 struct kvm_userspace_memory_region { 1362 __u32 slot; 1363 __u32 flags; 1364 __u64 guest_phys_addr; 1365 __u64 memory_size; /* bytes */ 1366 __u64 userspace_addr; /* start of the userspace allocated memory */ 1367 }; 1368 1369 /* for kvm_userspace_memory_region::flags */ 1370 #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) 1371 #define KVM_MEM_READONLY (1UL << 1) 1372 1373This ioctl allows the user to create, modify or delete a guest physical 1374memory slot. Bits 0-15 of "slot" specify the slot id and this value 1375should be less than the maximum number of user memory slots supported per 1376VM. The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS. 1377Slots may not overlap in guest physical address space. 1378 1379If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot" 1380specifies the address space which is being modified. They must be 1381less than the value that KVM_CHECK_EXTENSION returns for the 1382KVM_CAP_MULTI_ADDRESS_SPACE capability. Slots in separate address spaces 1383are unrelated; the restriction on overlapping slots only applies within 1384each address space. 1385 1386Deleting a slot is done by passing zero for memory_size. When changing 1387an existing slot, it may be moved in the guest physical memory space, 1388or its flags may be modified, but it may not be resized. 1389 1390Memory for the region is taken starting at the address denoted by the 1391field userspace_addr, which must point at user addressable memory for 1392the entire memory slot size. Any object may back this memory, including 1393anonymous memory, ordinary files, and hugetlbfs. 1394 1395On architectures that support a form of address tagging, userspace_addr must 1396be an untagged address. 1397 1398It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr 1399be identical. This allows large pages in the guest to be backed by large 1400pages in the host. 1401 1402The flags field supports two flags: KVM_MEM_LOG_DIRTY_PAGES and 1403KVM_MEM_READONLY. The former can be set to instruct KVM to keep track of 1404writes to memory within the slot. See KVM_GET_DIRTY_LOG ioctl to know how to 1405use it. The latter can be set, if KVM_CAP_READONLY_MEM capability allows it, 1406to make a new slot read-only. In this case, writes to this memory will be 1407posted to userspace as KVM_EXIT_MMIO exits. 1408 1409When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of 1410the memory region are automatically reflected into the guest. For example, an 1411mmap() that affects the region will be made visible immediately. Another 1412example is madvise(MADV_DROP). 1413 1414For TDX guest, deleting/moving memory region loses guest memory contents. 1415Read only region isn't supported. Only as-id 0 is supported. 1416 1417Note: On arm64, a write generated by the page-table walker (to update 1418the Access and Dirty flags, for example) never results in a 1419KVM_EXIT_MMIO exit when the slot has the KVM_MEM_READONLY flag. This 1420is because KVM cannot provide the data that would be written by the 1421page-table walker, making it impossible to emulate the access. 1422Instead, an abort (data abort if the cause of the page-table update 1423was a load or a store, instruction abort if it was an instruction 1424fetch) is injected in the guest. 1425 1426S390: 1427^^^^^ 1428 1429Returns -EINVAL or -EEXIST if the VM has the KVM_VM_S390_UCONTROL flag set. 1430Returns -EINVAL if called on a protected VM. 1431 14324.36 KVM_SET_TSS_ADDR 1433--------------------- 1434 1435:Capability: KVM_CAP_SET_TSS_ADDR 1436:Architectures: x86 1437:Type: vm ioctl 1438:Parameters: unsigned long tss_address (in) 1439:Returns: 0 on success, -1 on error 1440 1441This ioctl defines the physical address of a three-page region in the guest 1442physical address space. The region must be within the first 4GB of the 1443guest physical address space and must not conflict with any memory slot 1444or any mmio address. The guest may malfunction if it accesses this memory 1445region. 1446 1447This ioctl is required on Intel-based hosts. This is needed on Intel hardware 1448because of a quirk in the virtualization implementation (see the internals 1449documentation when it pops into existence). 1450 1451 1452.. _KVM_ENABLE_CAP: 1453 14544.37 KVM_ENABLE_CAP 1455------------------- 1456 1457:Capability: KVM_CAP_ENABLE_CAP 1458:Architectures: mips, ppc, s390, x86, loongarch 1459:Type: vcpu ioctl 1460:Parameters: struct kvm_enable_cap (in) 1461:Returns: 0 on success; -1 on error 1462 1463:Capability: KVM_CAP_ENABLE_CAP_VM 1464:Architectures: all 1465:Type: vm ioctl 1466:Parameters: struct kvm_enable_cap (in) 1467:Returns: 0 on success; -1 on error 1468 1469.. note:: 1470 1471 Not all extensions are enabled by default. Using this ioctl the application 1472 can enable an extension, making it available to the guest. 1473 1474On systems that do not support this ioctl, it always fails. On systems that 1475do support it, it only works for extensions that are supported for enablement. 1476 1477To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should 1478be used. 1479 1480:: 1481 1482 struct kvm_enable_cap { 1483 /* in */ 1484 __u32 cap; 1485 1486The capability that is supposed to get enabled. 1487 1488:: 1489 1490 __u32 flags; 1491 1492A bitfield indicating future enhancements. Has to be 0 for now. 1493 1494:: 1495 1496 __u64 args[4]; 1497 1498Arguments for enabling a feature. If a feature needs initial values to 1499function properly, this is the place to put them. 1500 1501:: 1502 1503 __u8 pad[64]; 1504 }; 1505 1506The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl 1507for vm-wide capabilities. 1508 15094.38 KVM_GET_MP_STATE 1510--------------------- 1511 1512:Capability: KVM_CAP_MP_STATE 1513:Architectures: x86, s390, arm64, riscv, loongarch 1514:Type: vcpu ioctl 1515:Parameters: struct kvm_mp_state (out) 1516:Returns: 0 on success; -1 on error 1517 1518:: 1519 1520 struct kvm_mp_state { 1521 __u32 mp_state; 1522 }; 1523 1524Returns the vcpu's current "multiprocessing state" (though also valid on 1525uniprocessor guests). 1526 1527Possible values are: 1528 1529 ========================== =============================================== 1530 KVM_MP_STATE_RUNNABLE the vcpu is currently running 1531 [x86,arm64,riscv,loongarch] 1532 KVM_MP_STATE_UNINITIALIZED the vcpu is an application processor (AP) 1533 which has not yet received an INIT signal [x86] 1534 KVM_MP_STATE_INIT_RECEIVED the vcpu has received an INIT signal, and is 1535 now ready for a SIPI [x86] 1536 KVM_MP_STATE_HALTED the vcpu has executed a HLT instruction and 1537 is waiting for an interrupt [x86] 1538 KVM_MP_STATE_SIPI_RECEIVED the vcpu has just received a SIPI (vector 1539 accessible via KVM_GET_VCPU_EVENTS) [x86] 1540 KVM_MP_STATE_STOPPED the vcpu is stopped [s390,arm64,riscv] 1541 KVM_MP_STATE_CHECK_STOP the vcpu is in a special error state [s390] 1542 KVM_MP_STATE_OPERATING the vcpu is operating (running or halted) 1543 [s390] 1544 KVM_MP_STATE_LOAD the vcpu is in a special load/startup state 1545 [s390] 1546 KVM_MP_STATE_SUSPENDED the vcpu is in a suspend state and is waiting 1547 for a wakeup event [arm64] 1548 ========================== =============================================== 1549 1550On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an 1551in-kernel irqchip, the multiprocessing state must be maintained by userspace on 1552these architectures. 1553 1554For arm64: 1555^^^^^^^^^^ 1556 1557If a vCPU is in the KVM_MP_STATE_SUSPENDED state, KVM will emulate the 1558architectural execution of a WFI instruction. 1559 1560If a wakeup event is recognized, KVM will exit to userspace with a 1561KVM_SYSTEM_EVENT exit, where the event type is KVM_SYSTEM_EVENT_WAKEUP. If 1562userspace wants to honor the wakeup, it must set the vCPU's MP state to 1563KVM_MP_STATE_RUNNABLE. If it does not, KVM will continue to await a wakeup 1564event in subsequent calls to KVM_RUN. 1565 1566.. warning:: 1567 1568 If userspace intends to keep the vCPU in a SUSPENDED state, it is 1569 strongly recommended that userspace take action to suppress the 1570 wakeup event (such as masking an interrupt). Otherwise, subsequent 1571 calls to KVM_RUN will immediately exit with a KVM_SYSTEM_EVENT_WAKEUP 1572 event and inadvertently waste CPU cycles. 1573 1574 Additionally, if userspace takes action to suppress a wakeup event, 1575 it is strongly recommended that it also restores the vCPU to its 1576 original state when the vCPU is made RUNNABLE again. For example, 1577 if userspace masked a pending interrupt to suppress the wakeup, 1578 the interrupt should be unmasked before returning control to the 1579 guest. 1580 1581For riscv: 1582^^^^^^^^^^ 1583 1584The only states that are valid are KVM_MP_STATE_STOPPED and 1585KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not. 1586 1587On LoongArch, only the KVM_MP_STATE_RUNNABLE state is used to reflect 1588whether the vcpu is runnable. 1589 15904.39 KVM_SET_MP_STATE 1591--------------------- 1592 1593:Capability: KVM_CAP_MP_STATE 1594:Architectures: x86, s390, arm64, riscv, loongarch 1595:Type: vcpu ioctl 1596:Parameters: struct kvm_mp_state (in) 1597:Returns: 0 on success; -1 on error 1598 1599Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for 1600arguments. 1601 1602On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an 1603in-kernel irqchip, the multiprocessing state must be maintained by userspace on 1604these architectures. 1605 1606For arm64/riscv: 1607^^^^^^^^^^^^^^^^ 1608 1609The only states that are valid are KVM_MP_STATE_STOPPED and 1610KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not. 1611 1612On LoongArch, only the KVM_MP_STATE_RUNNABLE state is used to reflect 1613whether the vcpu is runnable. 1614 16154.40 KVM_SET_IDENTITY_MAP_ADDR 1616------------------------------ 1617 1618:Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR 1619:Architectures: x86 1620:Type: vm ioctl 1621:Parameters: unsigned long identity (in) 1622:Returns: 0 on success, -1 on error 1623 1624This ioctl defines the physical address of a one-page region in the guest 1625physical address space. The region must be within the first 4GB of the 1626guest physical address space and must not conflict with any memory slot 1627or any mmio address. The guest may malfunction if it accesses this memory 1628region. 1629 1630Setting the address to 0 will result in resetting the address to its default 1631(0xfffbc000). 1632 1633This ioctl is required on Intel-based hosts. This is needed on Intel hardware 1634because of a quirk in the virtualization implementation (see the internals 1635documentation when it pops into existence). 1636 1637Fails if any VCPU has already been created. 1638 16394.41 KVM_SET_BOOT_CPU_ID 1640------------------------ 1641 1642:Capability: KVM_CAP_SET_BOOT_CPU_ID 1643:Architectures: x86 1644:Type: vm ioctl 1645:Parameters: unsigned long vcpu_id 1646:Returns: 0 on success, -1 on error 1647 1648Define which vcpu is the Bootstrap Processor (BSP). Values are the same 1649as the vcpu id in KVM_CREATE_VCPU. If this ioctl is not called, the default 1650is vcpu 0. This ioctl has to be called before vcpu creation, 1651otherwise it will return EBUSY error. 1652 1653 16544.42 KVM_GET_XSAVE 1655------------------ 1656 1657:Capability: KVM_CAP_XSAVE 1658:Architectures: x86 1659:Type: vcpu ioctl 1660:Parameters: struct kvm_xsave (out) 1661:Returns: 0 on success, -1 on error 1662 1663 1664:: 1665 1666 struct kvm_xsave { 1667 __u32 region[1024]; 1668 __u32 extra[0]; 1669 }; 1670 1671This ioctl would copy current vcpu's xsave struct to the userspace. 1672 1673 16744.43 KVM_SET_XSAVE 1675------------------ 1676 1677:Capability: KVM_CAP_XSAVE and KVM_CAP_XSAVE2 1678:Architectures: x86 1679:Type: vcpu ioctl 1680:Parameters: struct kvm_xsave (in) 1681:Returns: 0 on success, -1 on error 1682 1683:: 1684 1685 1686 struct kvm_xsave { 1687 __u32 region[1024]; 1688 __u32 extra[0]; 1689 }; 1690 1691This ioctl would copy userspace's xsave struct to the kernel. It copies 1692as many bytes as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2), 1693when invoked on the vm file descriptor. The size value returned by 1694KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) will always be at least 4096. 1695Currently, it is only greater than 4096 if a dynamic feature has been 1696enabled with ``arch_prctl()``, but this may change in the future. 1697 1698The offsets of the state save areas in struct kvm_xsave follow the 1699contents of CPUID leaf 0xD on the host. 1700 1701 17024.44 KVM_GET_XCRS 1703----------------- 1704 1705:Capability: KVM_CAP_XCRS 1706:Architectures: x86 1707:Type: vcpu ioctl 1708:Parameters: struct kvm_xcrs (out) 1709:Returns: 0 on success, -1 on error 1710 1711:: 1712 1713 struct kvm_xcr { 1714 __u32 xcr; 1715 __u32 reserved; 1716 __u64 value; 1717 }; 1718 1719 struct kvm_xcrs { 1720 __u32 nr_xcrs; 1721 __u32 flags; 1722 struct kvm_xcr xcrs[KVM_MAX_XCRS]; 1723 __u64 padding[16]; 1724 }; 1725 1726This ioctl would copy current vcpu's xcrs to the userspace. 1727 1728 17294.45 KVM_SET_XCRS 1730----------------- 1731 1732:Capability: KVM_CAP_XCRS 1733:Architectures: x86 1734:Type: vcpu ioctl 1735:Parameters: struct kvm_xcrs (in) 1736:Returns: 0 on success, -1 on error 1737 1738:: 1739 1740 struct kvm_xcr { 1741 __u32 xcr; 1742 __u32 reserved; 1743 __u64 value; 1744 }; 1745 1746 struct kvm_xcrs { 1747 __u32 nr_xcrs; 1748 __u32 flags; 1749 struct kvm_xcr xcrs[KVM_MAX_XCRS]; 1750 __u64 padding[16]; 1751 }; 1752 1753This ioctl would set vcpu's xcr to the value userspace specified. 1754 1755 17564.46 KVM_GET_SUPPORTED_CPUID 1757---------------------------- 1758 1759:Capability: KVM_CAP_EXT_CPUID 1760:Architectures: x86 1761:Type: system ioctl 1762:Parameters: struct kvm_cpuid2 (in/out) 1763:Returns: 0 on success, -1 on error 1764 1765:: 1766 1767 struct kvm_cpuid2 { 1768 __u32 nent; 1769 __u32 padding; 1770 struct kvm_cpuid_entry2 entries[0]; 1771 }; 1772 1773 #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) 1774 #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) /* deprecated */ 1775 #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) /* deprecated */ 1776 1777 struct kvm_cpuid_entry2 { 1778 __u32 function; 1779 __u32 index; 1780 __u32 flags; 1781 __u32 eax; 1782 __u32 ebx; 1783 __u32 ecx; 1784 __u32 edx; 1785 __u32 padding[3]; 1786 }; 1787 1788This ioctl returns x86 cpuid features which are supported by both the 1789hardware and kvm in its default configuration. Userspace can use the 1790information returned by this ioctl to construct cpuid information (for 1791KVM_SET_CPUID2) that is consistent with hardware, kernel, and 1792userspace capabilities, and with user requirements (for example, the 1793user may wish to constrain cpuid to emulate older hardware, or for 1794feature consistency across a cluster). 1795 1796Dynamically-enabled feature bits need to be requested with 1797``arch_prctl()`` before calling this ioctl. Feature bits that have not 1798been requested are excluded from the result. 1799 1800Note that certain capabilities, such as KVM_CAP_X86_DISABLE_EXITS, may 1801expose cpuid features (e.g. MONITOR) which are not supported by kvm in 1802its default configuration. If userspace enables such capabilities, it 1803is responsible for modifying the results of this ioctl appropriately. 1804 1805Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure 1806with the 'nent' field indicating the number of entries in the variable-size 1807array 'entries'. If the number of entries is too low to describe the cpu 1808capabilities, an error (E2BIG) is returned. If the number is too high, 1809the 'nent' field is adjusted and an error (ENOMEM) is returned. If the 1810number is just right, the 'nent' field is adjusted to the number of valid 1811entries in the 'entries' array, which is then filled. 1812 1813The entries returned are the host cpuid as returned by the cpuid instruction, 1814with unknown or unsupported features masked out. Some features (for example, 1815x2apic), may not be present in the host cpu, but are exposed by kvm if it can 1816emulate them efficiently. The fields in each entry are defined as follows: 1817 1818 function: 1819 the eax value used to obtain the entry 1820 1821 index: 1822 the ecx value used to obtain the entry (for entries that are 1823 affected by ecx) 1824 1825 flags: 1826 an OR of zero or more of the following: 1827 1828 KVM_CPUID_FLAG_SIGNIFCANT_INDEX: 1829 if the index field is valid 1830 1831 eax, ebx, ecx, edx: 1832 the values returned by the cpuid instruction for 1833 this function/index combination 1834 1835x2APIC (CPUID leaf 1, ecx[21) and TSC deadline timer (CPUID leaf 1, ecx[24]) 1836may be returned as true, but they depend on KVM_CREATE_IRQCHIP for in-kernel 1837emulation of the local APIC. TSC deadline timer support is also reported via:: 1838 1839 ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER) 1840 1841if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the 1842feature in userspace, then you can enable the feature for KVM_SET_CPUID2. 1843 1844Enabling x2APIC in KVM_SET_CPUID2 requires KVM_CREATE_IRQCHIP as KVM doesn't 1845support forwarding x2APIC MSR accesses to userspace, i.e. KVM does not support 1846emulating x2APIC in userspace. 1847 18484.47 KVM_PPC_GET_PVINFO 1849----------------------- 1850 1851:Capability: KVM_CAP_PPC_GET_PVINFO 1852:Architectures: ppc 1853:Type: vm ioctl 1854:Parameters: struct kvm_ppc_pvinfo (out) 1855:Returns: 0 on success, !0 on error 1856 1857:: 1858 1859 struct kvm_ppc_pvinfo { 1860 __u32 flags; 1861 __u32 hcall[4]; 1862 __u8 pad[108]; 1863 }; 1864 1865This ioctl fetches PV specific information that need to be passed to the guest 1866using the device tree or other means from vm context. 1867 1868The hcall array defines 4 instructions that make up a hypercall. 1869 1870If any additional field gets added to this structure later on, a bit for that 1871additional piece of information will be set in the flags bitmap. 1872 1873The flags bitmap is defined as:: 1874 1875 /* the host supports the ePAPR idle hcall 1876 #define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) 1877 18784.52 KVM_SET_GSI_ROUTING 1879------------------------ 1880 1881:Capability: KVM_CAP_IRQ_ROUTING 1882:Architectures: x86 s390 arm64 1883:Type: vm ioctl 1884:Parameters: struct kvm_irq_routing (in) 1885:Returns: 0 on success, -1 on error 1886 1887Sets the GSI routing table entries, overwriting any previously set entries. 1888 1889On arm64, GSI routing has the following limitation: 1890 1891- GSI routing does not apply to KVM_IRQ_LINE but only to KVM_IRQFD. 1892 1893:: 1894 1895 struct kvm_irq_routing { 1896 __u32 nr; 1897 __u32 flags; 1898 struct kvm_irq_routing_entry entries[0]; 1899 }; 1900 1901No flags are specified so far, the corresponding field must be set to zero. 1902 1903:: 1904 1905 struct kvm_irq_routing_entry { 1906 __u32 gsi; 1907 __u32 type; 1908 __u32 flags; 1909 __u32 pad; 1910 union { 1911 struct kvm_irq_routing_irqchip irqchip; 1912 struct kvm_irq_routing_msi msi; 1913 struct kvm_irq_routing_s390_adapter adapter; 1914 struct kvm_irq_routing_hv_sint hv_sint; 1915 struct kvm_irq_routing_xen_evtchn xen_evtchn; 1916 __u32 pad[8]; 1917 } u; 1918 }; 1919 1920 /* gsi routing entry types */ 1921 #define KVM_IRQ_ROUTING_IRQCHIP 1 1922 #define KVM_IRQ_ROUTING_MSI 2 1923 #define KVM_IRQ_ROUTING_S390_ADAPTER 3 1924 #define KVM_IRQ_ROUTING_HV_SINT 4 1925 #define KVM_IRQ_ROUTING_XEN_EVTCHN 5 1926 1927On s390, adding a KVM_IRQ_ROUTING_S390_ADAPTER is rejected on ucontrol VMs with 1928error -EINVAL. 1929 1930flags: 1931 1932- KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry 1933 type, specifies that the devid field contains a valid value. The per-VM 1934 KVM_CAP_MSI_DEVID capability advertises the requirement to provide 1935 the device ID. If this capability is not available, userspace should 1936 never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail. 1937- zero otherwise 1938 1939:: 1940 1941 struct kvm_irq_routing_irqchip { 1942 __u32 irqchip; 1943 __u32 pin; 1944 }; 1945 1946 struct kvm_irq_routing_msi { 1947 __u32 address_lo; 1948 __u32 address_hi; 1949 __u32 data; 1950 union { 1951 __u32 pad; 1952 __u32 devid; 1953 }; 1954 }; 1955 1956If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier 1957for the device that wrote the MSI message. For PCI, this is usually a 1958BDF identifier in the lower 16 bits. 1959 1960On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS 1961feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled, 1962address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of 1963address_hi must be zero. 1964 1965:: 1966 1967 struct kvm_irq_routing_s390_adapter { 1968 __u64 ind_addr; 1969 __u64 summary_addr; 1970 __u64 ind_offset; 1971 __u32 summary_offset; 1972 __u32 adapter_id; 1973 }; 1974 1975 struct kvm_irq_routing_hv_sint { 1976 __u32 vcpu; 1977 __u32 sint; 1978 }; 1979 1980 struct kvm_irq_routing_xen_evtchn { 1981 __u32 port; 1982 __u32 vcpu; 1983 __u32 priority; 1984 }; 1985 1986 1987When KVM_CAP_XEN_HVM includes the KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL bit 1988in its indication of supported features, routing to Xen event channels 1989is supported. Although the priority field is present, only the value 1990KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL is supported, which means delivery by 19912 level event channels. FIFO event channel support may be added in 1992the future. 1993 1994 19954.55 KVM_SET_TSC_KHZ 1996-------------------- 1997 1998:Capability: KVM_CAP_TSC_CONTROL / KVM_CAP_VM_TSC_CONTROL 1999:Architectures: x86 2000:Type: vcpu ioctl / vm ioctl 2001:Parameters: virtual tsc_khz 2002:Returns: 0 on success, -1 on error 2003 2004Specifies the tsc frequency for the virtual machine. The unit of the 2005frequency is KHz. 2006 2007If the KVM_CAP_VM_TSC_CONTROL capability is advertised, this can also 2008be used as a vm ioctl to set the initial tsc frequency of subsequently 2009created vCPUs. 2010 20114.56 KVM_GET_TSC_KHZ 2012-------------------- 2013 2014:Capability: KVM_CAP_GET_TSC_KHZ / KVM_CAP_VM_TSC_CONTROL 2015:Architectures: x86 2016:Type: vcpu ioctl / vm ioctl 2017:Parameters: none 2018:Returns: virtual tsc-khz on success, negative value on error 2019 2020Returns the tsc frequency of the guest. The unit of the return value is 2021KHz. If the host has unstable tsc this ioctl returns -EIO instead as an 2022error. 2023 2024 20254.57 KVM_GET_LAPIC 2026------------------ 2027 2028:Capability: KVM_CAP_IRQCHIP 2029:Architectures: x86 2030:Type: vcpu ioctl 2031:Parameters: struct kvm_lapic_state (out) 2032:Returns: 0 on success, -1 on error 2033 2034:: 2035 2036 #define KVM_APIC_REG_SIZE 0x400 2037 struct kvm_lapic_state { 2038 char regs[KVM_APIC_REG_SIZE]; 2039 }; 2040 2041Reads the Local APIC registers and copies them into the input argument. The 2042data format and layout are the same as documented in the architecture manual. 2043 2044If KVM_X2APIC_API_USE_32BIT_IDS feature of KVM_CAP_X2APIC_API is 2045enabled, then the format of APIC_ID register depends on the APIC mode 2046(reported by MSR_IA32_APICBASE) of its VCPU. x2APIC stores APIC ID in 2047the APIC_ID register (bytes 32-35). xAPIC only allows an 8-bit APIC ID 2048which is stored in bits 31-24 of the APIC register, or equivalently in 2049byte 35 of struct kvm_lapic_state's regs field. KVM_GET_LAPIC must then 2050be called after MSR_IA32_APICBASE has been set with KVM_SET_MSR. 2051 2052If KVM_X2APIC_API_USE_32BIT_IDS feature is disabled, struct kvm_lapic_state 2053always uses xAPIC format. 2054 2055 20564.58 KVM_SET_LAPIC 2057------------------ 2058 2059:Capability: KVM_CAP_IRQCHIP 2060:Architectures: x86 2061:Type: vcpu ioctl 2062:Parameters: struct kvm_lapic_state (in) 2063:Returns: 0 on success, -1 on error 2064 2065:: 2066 2067 #define KVM_APIC_REG_SIZE 0x400 2068 struct kvm_lapic_state { 2069 char regs[KVM_APIC_REG_SIZE]; 2070 }; 2071 2072Copies the input argument into the Local APIC registers. The data format 2073and layout are the same as documented in the architecture manual. 2074 2075The format of the APIC ID register (bytes 32-35 of struct kvm_lapic_state's 2076regs field) depends on the state of the KVM_CAP_X2APIC_API capability. 2077See the note in KVM_GET_LAPIC. 2078 2079 20804.59 KVM_IOEVENTFD 2081------------------ 2082 2083:Capability: KVM_CAP_IOEVENTFD 2084:Architectures: all 2085:Type: vm ioctl 2086:Parameters: struct kvm_ioeventfd (in) 2087:Returns: 0 on success, !0 on error 2088 2089This ioctl attaches or detaches an ioeventfd to a legal pio/mmio address 2090within the guest. A guest write in the registered address will signal the 2091provided event instead of triggering an exit. 2092 2093:: 2094 2095 struct kvm_ioeventfd { 2096 __u64 datamatch; 2097 __u64 addr; /* legal pio/mmio address */ 2098 __u32 len; /* 0, 1, 2, 4, or 8 bytes */ 2099 __s32 fd; 2100 __u32 flags; 2101 __u8 pad[36]; 2102 }; 2103 2104For the special case of virtio-ccw devices on s390, the ioevent is matched 2105to a subchannel/virtqueue tuple instead. 2106 2107The following flags are defined:: 2108 2109 #define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch) 2110 #define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio) 2111 #define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign) 2112 #define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \ 2113 (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify) 2114 2115If datamatch flag is set, the event will be signaled only if the written value 2116to the registered address is equal to datamatch in struct kvm_ioeventfd. 2117 2118For virtio-ccw devices, addr contains the subchannel id and datamatch the 2119virtqueue index. 2120 2121With KVM_CAP_IOEVENTFD_ANY_LENGTH, a zero length ioeventfd is allowed, and 2122the kernel will ignore the length of guest write and may get a faster vmexit. 2123The speedup may only apply to specific architectures, but the ioeventfd will 2124work anyway. 2125 21264.60 KVM_DIRTY_TLB 2127------------------ 2128 2129:Capability: KVM_CAP_SW_TLB 2130:Architectures: ppc 2131:Type: vcpu ioctl 2132:Parameters: struct kvm_dirty_tlb (in) 2133:Returns: 0 on success, -1 on error 2134 2135:: 2136 2137 struct kvm_dirty_tlb { 2138 __u64 bitmap; 2139 __u32 num_dirty; 2140 }; 2141 2142This must be called whenever userspace has changed an entry in the shared 2143TLB, prior to calling KVM_RUN on the associated vcpu. 2144 2145The "bitmap" field is the userspace address of an array. This array 2146consists of a number of bits, equal to the total number of TLB entries as 2147determined by the last successful call to ``KVM_ENABLE_CAP(KVM_CAP_SW_TLB)``, 2148rounded up to the nearest multiple of 64. 2149 2150Each bit corresponds to one TLB entry, ordered the same as in the shared TLB 2151array. 2152 2153The array is little-endian: the bit 0 is the least significant bit of the 2154first byte, bit 8 is the least significant bit of the second byte, etc. 2155This avoids any complications with differing word sizes. 2156 2157The "num_dirty" field is a performance hint for KVM to determine whether it 2158should skip processing the bitmap and just invalidate everything. It must 2159be set to the number of set bits in the bitmap. 2160 2161 21624.62 KVM_CREATE_SPAPR_TCE 2163------------------------- 2164 2165:Capability: KVM_CAP_SPAPR_TCE 2166:Architectures: powerpc 2167:Type: vm ioctl 2168:Parameters: struct kvm_create_spapr_tce (in) 2169:Returns: file descriptor for manipulating the created TCE table 2170 2171This creates a virtual TCE (translation control entry) table, which 2172is an IOMMU for PAPR-style virtual I/O. It is used to translate 2173logical addresses used in virtual I/O into guest physical addresses, 2174and provides a scatter/gather capability for PAPR virtual I/O. 2175 2176:: 2177 2178 /* for KVM_CAP_SPAPR_TCE */ 2179 struct kvm_create_spapr_tce { 2180 __u64 liobn; 2181 __u32 window_size; 2182 }; 2183 2184The liobn field gives the logical IO bus number for which to create a 2185TCE table. The window_size field specifies the size of the DMA window 2186which this TCE table will translate - the table will contain one 64 2187bit TCE entry for every 4kiB of the DMA window. 2188 2189When the guest issues an H_PUT_TCE hcall on a liobn for which a TCE 2190table has been created using this ioctl(), the kernel will handle it 2191in real mode, updating the TCE table. H_PUT_TCE calls for other 2192liobns will cause a vm exit and must be handled by userspace. 2193 2194The return value is a file descriptor which can be passed to mmap(2) 2195to map the created TCE table into userspace. This lets userspace read 2196the entries written by kernel-handled H_PUT_TCE calls, and also lets 2197userspace update the TCE table directly which is useful in some 2198circumstances. 2199 2200 22014.64 KVM_NMI 2202------------ 2203 2204:Capability: KVM_CAP_USER_NMI 2205:Architectures: x86 2206:Type: vcpu ioctl 2207:Parameters: none 2208:Returns: 0 on success, -1 on error 2209 2210Queues an NMI on the thread's vcpu. Note this is well defined only 2211when KVM_CREATE_IRQCHIP has not been called, since this is an interface 2212between the virtual cpu core and virtual local APIC. After KVM_CREATE_IRQCHIP 2213has been called, this interface is completely emulated within the kernel. 2214 2215To use this to emulate the LINT1 input with KVM_CREATE_IRQCHIP, use the 2216following algorithm: 2217 2218 - pause the vcpu 2219 - read the local APIC's state (KVM_GET_LAPIC) 2220 - check whether changing LINT1 will queue an NMI (see the LVT entry for LINT1) 2221 - if so, issue KVM_NMI 2222 - resume the vcpu 2223 2224Some guests configure the LINT1 NMI input to cause a panic, aiding in 2225debugging. 2226 2227 22284.65 KVM_S390_UCAS_MAP 2229---------------------- 2230 2231:Capability: KVM_CAP_S390_UCONTROL 2232:Architectures: s390 2233:Type: vcpu ioctl 2234:Parameters: struct kvm_s390_ucas_mapping (in) 2235:Returns: 0 in case of success 2236 2237The parameter is defined like this:: 2238 2239 struct kvm_s390_ucas_mapping { 2240 __u64 user_addr; 2241 __u64 vcpu_addr; 2242 __u64 length; 2243 }; 2244 2245This ioctl maps the memory at "user_addr" with the length "length" to 2246the vcpu's address space starting at "vcpu_addr". All parameters need to 2247be aligned by 1 megabyte. 2248 2249 22504.66 KVM_S390_UCAS_UNMAP 2251------------------------ 2252 2253:Capability: KVM_CAP_S390_UCONTROL 2254:Architectures: s390 2255:Type: vcpu ioctl 2256:Parameters: struct kvm_s390_ucas_mapping (in) 2257:Returns: 0 in case of success 2258 2259The parameter is defined like this:: 2260 2261 struct kvm_s390_ucas_mapping { 2262 __u64 user_addr; 2263 __u64 vcpu_addr; 2264 __u64 length; 2265 }; 2266 2267This ioctl unmaps the memory in the vcpu's address space starting at 2268"vcpu_addr" with the length "length". The field "user_addr" is ignored. 2269All parameters need to be aligned by 1 megabyte. 2270 2271 22724.67 KVM_S390_VCPU_FAULT 2273------------------------ 2274 2275:Capability: KVM_CAP_S390_UCONTROL 2276:Architectures: s390 2277:Type: vcpu ioctl 2278:Parameters: vcpu absolute address (in) 2279:Returns: 0 in case of success 2280 2281This call creates a page table entry on the virtual cpu's address space 2282(for user controlled virtual machines) or the virtual machine's address 2283space (for regular virtual machines). This only works for minor faults, 2284thus it's recommended to access subject memory page via the user page 2285table upfront. This is useful to handle validity intercepts for user 2286controlled virtual machines to fault in the virtual cpu's lowcore pages 2287prior to calling the KVM_RUN ioctl. 2288 2289 22904.68 KVM_SET_ONE_REG 2291-------------------- 2292 2293:Capability: KVM_CAP_ONE_REG 2294:Architectures: all 2295:Type: vcpu ioctl 2296:Parameters: struct kvm_one_reg (in) 2297:Returns: 0 on success, negative value on failure 2298 2299Errors: 2300 2301 ====== ============================================================ 2302 ENOENT no such register 2303 EINVAL invalid register ID, or no such register or used with VMs in 2304 protected virtualization mode on s390 2305 EPERM (arm64) register access not allowed before vcpu finalization 2306 EBUSY (riscv) changing register value not allowed after the vcpu 2307 has run at least once 2308 ====== ============================================================ 2309 2310(These error codes are indicative only: do not rely on a specific error 2311code being returned in a specific situation.) 2312 2313:: 2314 2315 struct kvm_one_reg { 2316 __u64 id; 2317 __u64 addr; 2318 }; 2319 2320Using this ioctl, a single vcpu register can be set to a specific value 2321defined by user space with the passed in struct kvm_one_reg, where id 2322refers to the register identifier as described below and addr is a pointer 2323to a variable with the respective size. There can be architecture agnostic 2324and architecture specific registers. Each have their own range of operation 2325and their own constants and width. To keep track of the implemented 2326registers, find a list below: 2327 2328 ======= =============================== ============ 2329 Arch Register Width (bits) 2330 ======= =============================== ============ 2331 PPC KVM_REG_PPC_HIOR 64 2332 PPC KVM_REG_PPC_IAC1 64 2333 PPC KVM_REG_PPC_IAC2 64 2334 PPC KVM_REG_PPC_IAC3 64 2335 PPC KVM_REG_PPC_IAC4 64 2336 PPC KVM_REG_PPC_DAC1 64 2337 PPC KVM_REG_PPC_DAC2 64 2338 PPC KVM_REG_PPC_DABR 64 2339 PPC KVM_REG_PPC_DSCR 64 2340 PPC KVM_REG_PPC_PURR 64 2341 PPC KVM_REG_PPC_SPURR 64 2342 PPC KVM_REG_PPC_DAR 64 2343 PPC KVM_REG_PPC_DSISR 32 2344 PPC KVM_REG_PPC_AMR 64 2345 PPC KVM_REG_PPC_UAMOR 64 2346 PPC KVM_REG_PPC_MMCR0 64 2347 PPC KVM_REG_PPC_MMCR1 64 2348 PPC KVM_REG_PPC_MMCRA 64 2349 PPC KVM_REG_PPC_MMCR2 64 2350 PPC KVM_REG_PPC_MMCRS 64 2351 PPC KVM_REG_PPC_MMCR3 64 2352 PPC KVM_REG_PPC_SIAR 64 2353 PPC KVM_REG_PPC_SDAR 64 2354 PPC KVM_REG_PPC_SIER 64 2355 PPC KVM_REG_PPC_SIER2 64 2356 PPC KVM_REG_PPC_SIER3 64 2357 PPC KVM_REG_PPC_PMC1 32 2358 PPC KVM_REG_PPC_PMC2 32 2359 PPC KVM_REG_PPC_PMC3 32 2360 PPC KVM_REG_PPC_PMC4 32 2361 PPC KVM_REG_PPC_PMC5 32 2362 PPC KVM_REG_PPC_PMC6 32 2363 PPC KVM_REG_PPC_PMC7 32 2364 PPC KVM_REG_PPC_PMC8 32 2365 PPC KVM_REG_PPC_FPR0 64 2366 ... 2367 PPC KVM_REG_PPC_FPR31 64 2368 PPC KVM_REG_PPC_VR0 128 2369 ... 2370 PPC KVM_REG_PPC_VR31 128 2371 PPC KVM_REG_PPC_VSR0 128 2372 ... 2373 PPC KVM_REG_PPC_VSR31 128 2374 PPC KVM_REG_PPC_FPSCR 64 2375 PPC KVM_REG_PPC_VSCR 32 2376 PPC KVM_REG_PPC_VPA_ADDR 64 2377 PPC KVM_REG_PPC_VPA_SLB 128 2378 PPC KVM_REG_PPC_VPA_DTL 128 2379 PPC KVM_REG_PPC_EPCR 32 2380 PPC KVM_REG_PPC_EPR 32 2381 PPC KVM_REG_PPC_TCR 32 2382 PPC KVM_REG_PPC_TSR 32 2383 PPC KVM_REG_PPC_OR_TSR 32 2384 PPC KVM_REG_PPC_CLEAR_TSR 32 2385 PPC KVM_REG_PPC_MAS0 32 2386 PPC KVM_REG_PPC_MAS1 32 2387 PPC KVM_REG_PPC_MAS2 64 2388 PPC KVM_REG_PPC_MAS7_3 64 2389 PPC KVM_REG_PPC_MAS4 32 2390 PPC KVM_REG_PPC_MAS6 32 2391 PPC KVM_REG_PPC_MMUCFG 32 2392 PPC KVM_REG_PPC_TLB0CFG 32 2393 PPC KVM_REG_PPC_TLB1CFG 32 2394 PPC KVM_REG_PPC_TLB2CFG 32 2395 PPC KVM_REG_PPC_TLB3CFG 32 2396 PPC KVM_REG_PPC_TLB0PS 32 2397 PPC KVM_REG_PPC_TLB1PS 32 2398 PPC KVM_REG_PPC_TLB2PS 32 2399 PPC KVM_REG_PPC_TLB3PS 32 2400 PPC KVM_REG_PPC_EPTCFG 32 2401 PPC KVM_REG_PPC_ICP_STATE 64 2402 PPC KVM_REG_PPC_VP_STATE 128 2403 PPC KVM_REG_PPC_TB_OFFSET 64 2404 PPC KVM_REG_PPC_SPMC1 32 2405 PPC KVM_REG_PPC_SPMC2 32 2406 PPC KVM_REG_PPC_IAMR 64 2407 PPC KVM_REG_PPC_TFHAR 64 2408 PPC KVM_REG_PPC_TFIAR 64 2409 PPC KVM_REG_PPC_TEXASR 64 2410 PPC KVM_REG_PPC_FSCR 64 2411 PPC KVM_REG_PPC_PSPB 32 2412 PPC KVM_REG_PPC_EBBHR 64 2413 PPC KVM_REG_PPC_EBBRR 64 2414 PPC KVM_REG_PPC_BESCR 64 2415 PPC KVM_REG_PPC_TAR 64 2416 PPC KVM_REG_PPC_DPDES 64 2417 PPC KVM_REG_PPC_DAWR 64 2418 PPC KVM_REG_PPC_DAWRX 64 2419 PPC KVM_REG_PPC_CIABR 64 2420 PPC KVM_REG_PPC_IC 64 2421 PPC KVM_REG_PPC_VTB 64 2422 PPC KVM_REG_PPC_CSIGR 64 2423 PPC KVM_REG_PPC_TACR 64 2424 PPC KVM_REG_PPC_TCSCR 64 2425 PPC KVM_REG_PPC_PID 64 2426 PPC KVM_REG_PPC_ACOP 64 2427 PPC KVM_REG_PPC_VRSAVE 32 2428 PPC KVM_REG_PPC_LPCR 32 2429 PPC KVM_REG_PPC_LPCR_64 64 2430 PPC KVM_REG_PPC_PPR 64 2431 PPC KVM_REG_PPC_ARCH_COMPAT 32 2432 PPC KVM_REG_PPC_DABRX 32 2433 PPC KVM_REG_PPC_WORT 64 2434 PPC KVM_REG_PPC_SPRG9 64 2435 PPC KVM_REG_PPC_DBSR 32 2436 PPC KVM_REG_PPC_TIDR 64 2437 PPC KVM_REG_PPC_PSSCR 64 2438 PPC KVM_REG_PPC_DEC_EXPIRY 64 2439 PPC KVM_REG_PPC_PTCR 64 2440 PPC KVM_REG_PPC_HASHKEYR 64 2441 PPC KVM_REG_PPC_HASHPKEYR 64 2442 PPC KVM_REG_PPC_DAWR1 64 2443 PPC KVM_REG_PPC_DAWRX1 64 2444 PPC KVM_REG_PPC_DEXCR 64 2445 PPC KVM_REG_PPC_TM_GPR0 64 2446 ... 2447 PPC KVM_REG_PPC_TM_GPR31 64 2448 PPC KVM_REG_PPC_TM_VSR0 128 2449 ... 2450 PPC KVM_REG_PPC_TM_VSR63 128 2451 PPC KVM_REG_PPC_TM_CR 64 2452 PPC KVM_REG_PPC_TM_LR 64 2453 PPC KVM_REG_PPC_TM_CTR 64 2454 PPC KVM_REG_PPC_TM_FPSCR 64 2455 PPC KVM_REG_PPC_TM_AMR 64 2456 PPC KVM_REG_PPC_TM_PPR 64 2457 PPC KVM_REG_PPC_TM_VRSAVE 64 2458 PPC KVM_REG_PPC_TM_VSCR 32 2459 PPC KVM_REG_PPC_TM_DSCR 64 2460 PPC KVM_REG_PPC_TM_TAR 64 2461 PPC KVM_REG_PPC_TM_XER 64 2462 2463 MIPS KVM_REG_MIPS_R0 64 2464 ... 2465 MIPS KVM_REG_MIPS_R31 64 2466 MIPS KVM_REG_MIPS_HI 64 2467 MIPS KVM_REG_MIPS_LO 64 2468 MIPS KVM_REG_MIPS_PC 64 2469 MIPS KVM_REG_MIPS_CP0_INDEX 32 2470 MIPS KVM_REG_MIPS_CP0_ENTRYLO0 64 2471 MIPS KVM_REG_MIPS_CP0_ENTRYLO1 64 2472 MIPS KVM_REG_MIPS_CP0_CONTEXT 64 2473 MIPS KVM_REG_MIPS_CP0_CONTEXTCONFIG 32 2474 MIPS KVM_REG_MIPS_CP0_USERLOCAL 64 2475 MIPS KVM_REG_MIPS_CP0_XCONTEXTCONFIG 64 2476 MIPS KVM_REG_MIPS_CP0_PAGEMASK 32 2477 MIPS KVM_REG_MIPS_CP0_PAGEGRAIN 32 2478 MIPS KVM_REG_MIPS_CP0_SEGCTL0 64 2479 MIPS KVM_REG_MIPS_CP0_SEGCTL1 64 2480 MIPS KVM_REG_MIPS_CP0_SEGCTL2 64 2481 MIPS KVM_REG_MIPS_CP0_PWBASE 64 2482 MIPS KVM_REG_MIPS_CP0_PWFIELD 64 2483 MIPS KVM_REG_MIPS_CP0_PWSIZE 64 2484 MIPS KVM_REG_MIPS_CP0_WIRED 32 2485 MIPS KVM_REG_MIPS_CP0_PWCTL 32 2486 MIPS KVM_REG_MIPS_CP0_HWRENA 32 2487 MIPS KVM_REG_MIPS_CP0_BADVADDR 64 2488 MIPS KVM_REG_MIPS_CP0_BADINSTR 32 2489 MIPS KVM_REG_MIPS_CP0_BADINSTRP 32 2490 MIPS KVM_REG_MIPS_CP0_COUNT 32 2491 MIPS KVM_REG_MIPS_CP0_ENTRYHI 64 2492 MIPS KVM_REG_MIPS_CP0_COMPARE 32 2493 MIPS KVM_REG_MIPS_CP0_STATUS 32 2494 MIPS KVM_REG_MIPS_CP0_INTCTL 32 2495 MIPS KVM_REG_MIPS_CP0_CAUSE 32 2496 MIPS KVM_REG_MIPS_CP0_EPC 64 2497 MIPS KVM_REG_MIPS_CP0_PRID 32 2498 MIPS KVM_REG_MIPS_CP0_EBASE 64 2499 MIPS KVM_REG_MIPS_CP0_CONFIG 32 2500 MIPS KVM_REG_MIPS_CP0_CONFIG1 32 2501 MIPS KVM_REG_MIPS_CP0_CONFIG2 32 2502 MIPS KVM_REG_MIPS_CP0_CONFIG3 32 2503 MIPS KVM_REG_MIPS_CP0_CONFIG4 32 2504 MIPS KVM_REG_MIPS_CP0_CONFIG5 32 2505 MIPS KVM_REG_MIPS_CP0_CONFIG7 32 2506 MIPS KVM_REG_MIPS_CP0_XCONTEXT 64 2507 MIPS KVM_REG_MIPS_CP0_ERROREPC 64 2508 MIPS KVM_REG_MIPS_CP0_KSCRATCH1 64 2509 MIPS KVM_REG_MIPS_CP0_KSCRATCH2 64 2510 MIPS KVM_REG_MIPS_CP0_KSCRATCH3 64 2511 MIPS KVM_REG_MIPS_CP0_KSCRATCH4 64 2512 MIPS KVM_REG_MIPS_CP0_KSCRATCH5 64 2513 MIPS KVM_REG_MIPS_CP0_KSCRATCH6 64 2514 MIPS KVM_REG_MIPS_CP0_MAAR(0..63) 64 2515 MIPS KVM_REG_MIPS_COUNT_CTL 64 2516 MIPS KVM_REG_MIPS_COUNT_RESUME 64 2517 MIPS KVM_REG_MIPS_COUNT_HZ 64 2518 MIPS KVM_REG_MIPS_FPR_32(0..31) 32 2519 MIPS KVM_REG_MIPS_FPR_64(0..31) 64 2520 MIPS KVM_REG_MIPS_VEC_128(0..31) 128 2521 MIPS KVM_REG_MIPS_FCR_IR 32 2522 MIPS KVM_REG_MIPS_FCR_CSR 32 2523 MIPS KVM_REG_MIPS_MSA_IR 32 2524 MIPS KVM_REG_MIPS_MSA_CSR 32 2525 ======= =============================== ============ 2526 2527ARM registers are mapped using the lower 32 bits. The upper 16 of that 2528is the register group type, or coprocessor number: 2529 2530ARM core registers have the following id bit patterns:: 2531 2532 0x4020 0000 0010 <index into the kvm_regs struct:16> 2533 2534ARM 32-bit CP15 registers have the following id bit patterns:: 2535 2536 0x4020 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3> 2537 2538ARM 64-bit CP15 registers have the following id bit patterns:: 2539 2540 0x4030 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3> 2541 2542ARM CCSIDR registers are demultiplexed by CSSELR value:: 2543 2544 0x4020 0000 0011 00 <csselr:8> 2545 2546ARM 32-bit VFP control registers have the following id bit patterns:: 2547 2548 0x4020 0000 0012 1 <regno:12> 2549 2550ARM 64-bit FP registers have the following id bit patterns:: 2551 2552 0x4030 0000 0012 0 <regno:12> 2553 2554ARM firmware pseudo-registers have the following bit pattern:: 2555 2556 0x4030 0000 0014 <regno:16> 2557 2558 2559arm64 registers are mapped using the lower 32 bits. The upper 16 of 2560that is the register group type, or coprocessor number: 2561 2562arm64 core/FP-SIMD registers have the following id bit patterns. Note 2563that the size of the access is variable, as the kvm_regs structure 2564contains elements ranging from 32 to 128 bits. The index is a 32bit 2565value in the kvm_regs structure seen as a 32bit array:: 2566 2567 0x60x0 0000 0010 <index into the kvm_regs struct:16> 2568 2569Specifically: 2570 2571======================= ========= ===== ======================================= 2572 Encoding Register Bits kvm_regs member 2573======================= ========= ===== ======================================= 2574 0x6030 0000 0010 0000 X0 64 regs.regs[0] 2575 0x6030 0000 0010 0002 X1 64 regs.regs[1] 2576 ... 2577 0x6030 0000 0010 003c X30 64 regs.regs[30] 2578 0x6030 0000 0010 003e SP 64 regs.sp 2579 0x6030 0000 0010 0040 PC 64 regs.pc 2580 0x6030 0000 0010 0042 PSTATE 64 regs.pstate 2581 0x6030 0000 0010 0044 SP_EL1 64 sp_el1 2582 0x6030 0000 0010 0046 ELR_EL1 64 elr_el1 2583 0x6030 0000 0010 0048 SPSR_EL1 64 spsr[KVM_SPSR_EL1] (alias SPSR_SVC) 2584 0x6030 0000 0010 004a SPSR_ABT 64 spsr[KVM_SPSR_ABT] 2585 0x6030 0000 0010 004c SPSR_UND 64 spsr[KVM_SPSR_UND] 2586 0x6030 0000 0010 004e SPSR_IRQ 64 spsr[KVM_SPSR_IRQ] 2587 0x6030 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ] 2588 0x6040 0000 0010 0054 V0 128 fp_regs.vregs[0] [1]_ 2589 0x6040 0000 0010 0058 V1 128 fp_regs.vregs[1] [1]_ 2590 ... 2591 0x6040 0000 0010 00d0 V31 128 fp_regs.vregs[31] [1]_ 2592 0x6020 0000 0010 00d4 FPSR 32 fp_regs.fpsr 2593 0x6020 0000 0010 00d5 FPCR 32 fp_regs.fpcr 2594======================= ========= ===== ======================================= 2595 2596.. [1] These encodings are not accepted for SVE-enabled vcpus. See 2597 :ref:`KVM_ARM_VCPU_INIT`. 2598 2599 The equivalent register content can be accessed via bits [127:0] of 2600 the corresponding SVE Zn registers instead for vcpus that have SVE 2601 enabled (see below). 2602 2603arm64 CCSIDR registers are demultiplexed by CSSELR value:: 2604 2605 0x6020 0000 0011 00 <csselr:8> 2606 2607arm64 system registers have the following id bit patterns:: 2608 2609 0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3> 2610 2611.. warning:: 2612 2613 Two system register IDs do not follow the specified pattern. These 2614 are KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT, which map to 2615 system registers CNTV_CVAL_EL0 and CNTVCT_EL0 respectively. These 2616 two had their values accidentally swapped, which means TIMER_CVAL is 2617 derived from the register encoding for CNTVCT_EL0 and TIMER_CNT is 2618 derived from the register encoding for CNTV_CVAL_EL0. As this is 2619 API, it must remain this way. 2620 2621arm64 firmware pseudo-registers have the following bit pattern:: 2622 2623 0x6030 0000 0014 <regno:16> 2624 2625arm64 SVE registers have the following bit patterns:: 2626 2627 0x6080 0000 0015 00 <n:5> <slice:5> Zn bits[2048*slice + 2047 : 2048*slice] 2628 0x6050 0000 0015 04 <n:4> <slice:5> Pn bits[256*slice + 255 : 256*slice] 2629 0x6050 0000 0015 060 <slice:5> FFR bits[256*slice + 255 : 256*slice] 2630 0x6060 0000 0015 ffff KVM_REG_ARM64_SVE_VLS pseudo-register 2631 2632Access to register IDs where 2048 * slice >= 128 * max_vq will fail with 2633ENOENT. max_vq is the vcpu's maximum supported vector length in 128-bit 2634quadwords: see [2]_ below. 2635 2636These registers are only accessible on vcpus for which SVE is enabled. 2637See KVM_ARM_VCPU_INIT for details. 2638 2639In addition, except for KVM_REG_ARM64_SVE_VLS, these registers are not 2640accessible until the vcpu's SVE configuration has been finalized 2641using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE). See KVM_ARM_VCPU_INIT 2642and KVM_ARM_VCPU_FINALIZE for more information about this procedure. 2643 2644KVM_REG_ARM64_SVE_VLS is a pseudo-register that allows the set of vector 2645lengths supported by the vcpu to be discovered and configured by 2646userspace. When transferred to or from user memory via KVM_GET_ONE_REG 2647or KVM_SET_ONE_REG, the value of this register is of type 2648__u64[KVM_ARM64_SVE_VLS_WORDS], and encodes the set of vector lengths as 2649follows:: 2650 2651 __u64 vector_lengths[KVM_ARM64_SVE_VLS_WORDS]; 2652 2653 if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX && 2654 ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >> 2655 ((vq - KVM_ARM64_SVE_VQ_MIN) % 64)) & 1)) 2656 /* Vector length vq * 16 bytes supported */ 2657 else 2658 /* Vector length vq * 16 bytes not supported */ 2659 2660.. [2] The maximum value vq for which the above condition is true is 2661 max_vq. This is the maximum vector length available to the guest on 2662 this vcpu, and determines which register slices are visible through 2663 this ioctl interface. 2664 2665(See Documentation/arch/arm64/sve.rst for an explanation of the "vq" 2666nomenclature.) 2667 2668KVM_REG_ARM64_SVE_VLS is only accessible after KVM_ARM_VCPU_INIT. 2669KVM_ARM_VCPU_INIT initialises it to the best set of vector lengths that 2670the host supports. 2671 2672Userspace may subsequently modify it if desired until the vcpu's SVE 2673configuration is finalized using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE). 2674 2675Apart from simply removing all vector lengths from the host set that 2676exceed some value, support for arbitrarily chosen sets of vector lengths 2677is hardware-dependent and may not be available. Attempting to configure 2678an invalid set of vector lengths via KVM_SET_ONE_REG will fail with 2679EINVAL. 2680 2681After the vcpu's SVE configuration is finalized, further attempts to 2682write this register will fail with EPERM. 2683 2684arm64 bitmap feature firmware pseudo-registers have the following bit pattern:: 2685 2686 0x6030 0000 0016 <regno:16> 2687 2688The bitmap feature firmware registers exposes the hypercall services that 2689are available for userspace to configure. The set bits corresponds to the 2690services that are available for the guests to access. By default, KVM 2691sets all the supported bits during VM initialization. The userspace can 2692discover the available services via KVM_GET_ONE_REG, and write back the 2693bitmap corresponding to the features that it wishes guests to see via 2694KVM_SET_ONE_REG. 2695 2696Note: These registers are immutable once any of the vCPUs of the VM has 2697run at least once. A KVM_SET_ONE_REG in such a scenario will return 2698a -EBUSY to userspace. 2699 2700(See Documentation/virt/kvm/arm/hypercalls.rst for more details.) 2701 2702 2703MIPS registers are mapped using the lower 32 bits. The upper 16 of that is 2704the register group type: 2705 2706MIPS core registers (see above) have the following id bit patterns:: 2707 2708 0x7030 0000 0000 <reg:16> 2709 2710MIPS CP0 registers (see KVM_REG_MIPS_CP0_* above) have the following id bit 2711patterns depending on whether they're 32-bit or 64-bit registers:: 2712 2713 0x7020 0000 0001 00 <reg:5> <sel:3> (32-bit) 2714 0x7030 0000 0001 00 <reg:5> <sel:3> (64-bit) 2715 2716Note: KVM_REG_MIPS_CP0_ENTRYLO0 and KVM_REG_MIPS_CP0_ENTRYLO1 are the MIPS64 2717versions of the EntryLo registers regardless of the word size of the host 2718hardware, host kernel, guest, and whether XPA is present in the guest, i.e. 2719with the RI and XI bits (if they exist) in bits 63 and 62 respectively, and 2720the PFNX field starting at bit 30. 2721 2722MIPS MAARs (see KVM_REG_MIPS_CP0_MAAR(*) above) have the following id bit 2723patterns:: 2724 2725 0x7030 0000 0001 01 <reg:8> 2726 2727MIPS KVM control registers (see above) have the following id bit patterns:: 2728 2729 0x7030 0000 0002 <reg:16> 2730 2731MIPS FPU registers (see KVM_REG_MIPS_FPR_{32,64}() above) have the following 2732id bit patterns depending on the size of the register being accessed. They are 2733always accessed according to the current guest FPU mode (Status.FR and 2734Config5.FRE), i.e. as the guest would see them, and they become unpredictable 2735if the guest FPU mode is changed. MIPS SIMD Architecture (MSA) vector 2736registers (see KVM_REG_MIPS_VEC_128() above) have similar patterns as they 2737overlap the FPU registers:: 2738 2739 0x7020 0000 0003 00 <0:3> <reg:5> (32-bit FPU registers) 2740 0x7030 0000 0003 00 <0:3> <reg:5> (64-bit FPU registers) 2741 0x7040 0000 0003 00 <0:3> <reg:5> (128-bit MSA vector registers) 2742 2743MIPS FPU control registers (see KVM_REG_MIPS_FCR_{IR,CSR} above) have the 2744following id bit patterns:: 2745 2746 0x7020 0000 0003 01 <0:3> <reg:5> 2747 2748MIPS MSA control registers (see KVM_REG_MIPS_MSA_{IR,CSR} above) have the 2749following id bit patterns:: 2750 2751 0x7020 0000 0003 02 <0:3> <reg:5> 2752 2753RISC-V registers are mapped using the lower 32 bits. The upper 8 bits of 2754that is the register group type. 2755 2756RISC-V config registers are meant for configuring a Guest VCPU and it has 2757the following id bit patterns:: 2758 2759 0x8020 0000 01 <index into the kvm_riscv_config struct:24> (32bit Host) 2760 0x8030 0000 01 <index into the kvm_riscv_config struct:24> (64bit Host) 2761 2762Following are the RISC-V config registers: 2763 2764======================= ========= ============================================= 2765 Encoding Register Description 2766======================= ========= ============================================= 2767 0x80x0 0000 0100 0000 isa ISA feature bitmap of Guest VCPU 2768======================= ========= ============================================= 2769 2770The isa config register can be read anytime but can only be written before 2771a Guest VCPU runs. It will have ISA feature bits matching underlying host 2772set by default. 2773 2774RISC-V core registers represent the general execution state of a Guest VCPU 2775and it has the following id bit patterns:: 2776 2777 0x8020 0000 02 <index into the kvm_riscv_core struct:24> (32bit Host) 2778 0x8030 0000 02 <index into the kvm_riscv_core struct:24> (64bit Host) 2779 2780Following are the RISC-V core registers: 2781 2782======================= ========= ============================================= 2783 Encoding Register Description 2784======================= ========= ============================================= 2785 0x80x0 0000 0200 0000 regs.pc Program counter 2786 0x80x0 0000 0200 0001 regs.ra Return address 2787 0x80x0 0000 0200 0002 regs.sp Stack pointer 2788 0x80x0 0000 0200 0003 regs.gp Global pointer 2789 0x80x0 0000 0200 0004 regs.tp Task pointer 2790 0x80x0 0000 0200 0005 regs.t0 Caller saved register 0 2791 0x80x0 0000 0200 0006 regs.t1 Caller saved register 1 2792 0x80x0 0000 0200 0007 regs.t2 Caller saved register 2 2793 0x80x0 0000 0200 0008 regs.s0 Callee saved register 0 2794 0x80x0 0000 0200 0009 regs.s1 Callee saved register 1 2795 0x80x0 0000 0200 000a regs.a0 Function argument (or return value) 0 2796 0x80x0 0000 0200 000b regs.a1 Function argument (or return value) 1 2797 0x80x0 0000 0200 000c regs.a2 Function argument 2 2798 0x80x0 0000 0200 000d regs.a3 Function argument 3 2799 0x80x0 0000 0200 000e regs.a4 Function argument 4 2800 0x80x0 0000 0200 000f regs.a5 Function argument 5 2801 0x80x0 0000 0200 0010 regs.a6 Function argument 6 2802 0x80x0 0000 0200 0011 regs.a7 Function argument 7 2803 0x80x0 0000 0200 0012 regs.s2 Callee saved register 2 2804 0x80x0 0000 0200 0013 regs.s3 Callee saved register 3 2805 0x80x0 0000 0200 0014 regs.s4 Callee saved register 4 2806 0x80x0 0000 0200 0015 regs.s5 Callee saved register 5 2807 0x80x0 0000 0200 0016 regs.s6 Callee saved register 6 2808 0x80x0 0000 0200 0017 regs.s7 Callee saved register 7 2809 0x80x0 0000 0200 0018 regs.s8 Callee saved register 8 2810 0x80x0 0000 0200 0019 regs.s9 Callee saved register 9 2811 0x80x0 0000 0200 001a regs.s10 Callee saved register 10 2812 0x80x0 0000 0200 001b regs.s11 Callee saved register 11 2813 0x80x0 0000 0200 001c regs.t3 Caller saved register 3 2814 0x80x0 0000 0200 001d regs.t4 Caller saved register 4 2815 0x80x0 0000 0200 001e regs.t5 Caller saved register 5 2816 0x80x0 0000 0200 001f regs.t6 Caller saved register 6 2817 0x80x0 0000 0200 0020 mode Privilege mode (1 = S-mode or 0 = U-mode) 2818======================= ========= ============================================= 2819 2820RISC-V csr registers represent the supervisor mode control/status registers 2821of a Guest VCPU and it has the following id bit patterns:: 2822 2823 0x8020 0000 03 <index into the kvm_riscv_csr struct:24> (32bit Host) 2824 0x8030 0000 03 <index into the kvm_riscv_csr struct:24> (64bit Host) 2825 2826Following are the RISC-V csr registers: 2827 2828======================= ========= ============================================= 2829 Encoding Register Description 2830======================= ========= ============================================= 2831 0x80x0 0000 0300 0000 sstatus Supervisor status 2832 0x80x0 0000 0300 0001 sie Supervisor interrupt enable 2833 0x80x0 0000 0300 0002 stvec Supervisor trap vector base 2834 0x80x0 0000 0300 0003 sscratch Supervisor scratch register 2835 0x80x0 0000 0300 0004 sepc Supervisor exception program counter 2836 0x80x0 0000 0300 0005 scause Supervisor trap cause 2837 0x80x0 0000 0300 0006 stval Supervisor bad address or instruction 2838 0x80x0 0000 0300 0007 sip Supervisor interrupt pending 2839 0x80x0 0000 0300 0008 satp Supervisor address translation and protection 2840======================= ========= ============================================= 2841 2842RISC-V timer registers represent the timer state of a Guest VCPU and it has 2843the following id bit patterns:: 2844 2845 0x8030 0000 04 <index into the kvm_riscv_timer struct:24> 2846 2847Following are the RISC-V timer registers: 2848 2849======================= ========= ============================================= 2850 Encoding Register Description 2851======================= ========= ============================================= 2852 0x8030 0000 0400 0000 frequency Time base frequency (read-only) 2853 0x8030 0000 0400 0001 time Time value visible to Guest 2854 0x8030 0000 0400 0002 compare Time compare programmed by Guest 2855 0x8030 0000 0400 0003 state Time compare state (1 = ON or 0 = OFF) 2856======================= ========= ============================================= 2857 2858RISC-V F-extension registers represent the single precision floating point 2859state of a Guest VCPU and it has the following id bit patterns:: 2860 2861 0x8020 0000 05 <index into the __riscv_f_ext_state struct:24> 2862 2863Following are the RISC-V F-extension registers: 2864 2865======================= ========= ============================================= 2866 Encoding Register Description 2867======================= ========= ============================================= 2868 0x8020 0000 0500 0000 f[0] Floating point register 0 2869 ... 2870 0x8020 0000 0500 001f f[31] Floating point register 31 2871 0x8020 0000 0500 0020 fcsr Floating point control and status register 2872======================= ========= ============================================= 2873 2874RISC-V D-extension registers represent the double precision floating point 2875state of a Guest VCPU and it has the following id bit patterns:: 2876 2877 0x8020 0000 06 <index into the __riscv_d_ext_state struct:24> (fcsr) 2878 0x8030 0000 06 <index into the __riscv_d_ext_state struct:24> (non-fcsr) 2879 2880Following are the RISC-V D-extension registers: 2881 2882======================= ========= ============================================= 2883 Encoding Register Description 2884======================= ========= ============================================= 2885 0x8030 0000 0600 0000 f[0] Floating point register 0 2886 ... 2887 0x8030 0000 0600 001f f[31] Floating point register 31 2888 0x8020 0000 0600 0020 fcsr Floating point control and status register 2889======================= ========= ============================================= 2890 2891LoongArch registers are mapped using the lower 32 bits. The upper 16 bits of 2892that is the register group type. 2893 2894LoongArch csr registers are used to control guest cpu or get status of guest 2895cpu, and they have the following id bit patterns:: 2896 2897 0x9030 0000 0001 00 <reg:5> <sel:3> (64-bit) 2898 2899LoongArch KVM control registers are used to implement some new defined functions 2900such as set vcpu counter or reset vcpu, and they have the following id bit patterns:: 2901 2902 0x9030 0000 0002 <reg:16> 2903 2904 29054.69 KVM_GET_ONE_REG 2906-------------------- 2907 2908:Capability: KVM_CAP_ONE_REG 2909:Architectures: all 2910:Type: vcpu ioctl 2911:Parameters: struct kvm_one_reg (in and out) 2912:Returns: 0 on success, negative value on failure 2913 2914Errors include: 2915 2916 ======== ============================================================ 2917 ENOENT no such register 2918 EINVAL invalid register ID, or no such register or used with VMs in 2919 protected virtualization mode on s390 2920 EPERM (arm64) register access not allowed before vcpu finalization 2921 ======== ============================================================ 2922 2923(These error codes are indicative only: do not rely on a specific error 2924code being returned in a specific situation.) 2925 2926This ioctl allows to receive the value of a single register implemented 2927in a vcpu. The register to read is indicated by the "id" field of the 2928kvm_one_reg struct passed in. On success, the register value can be found 2929at the memory location pointed to by "addr". 2930 2931The list of registers accessible using this interface is identical to the 2932list in 4.68. 2933 2934 29354.70 KVM_KVMCLOCK_CTRL 2936---------------------- 2937 2938:Capability: KVM_CAP_KVMCLOCK_CTRL 2939:Architectures: Any that implement pvclocks (currently x86 only) 2940:Type: vcpu ioctl 2941:Parameters: None 2942:Returns: 0 on success, -1 on error 2943 2944This ioctl sets a flag accessible to the guest indicating that the specified 2945vCPU has been paused by the host userspace. 2946 2947The host will set a flag in the pvclock structure that is checked from the 2948soft lockup watchdog. The flag is part of the pvclock structure that is 2949shared between guest and host, specifically the second bit of the flags 2950field of the pvclock_vcpu_time_info structure. It will be set exclusively by 2951the host and read/cleared exclusively by the guest. The guest operation of 2952checking and clearing the flag must be an atomic operation so 2953load-link/store-conditional, or equivalent must be used. There are two cases 2954where the guest will clear the flag: when the soft lockup watchdog timer resets 2955itself or when a soft lockup is detected. This ioctl can be called any time 2956after pausing the vcpu, but before it is resumed. 2957 2958 29594.71 KVM_SIGNAL_MSI 2960------------------- 2961 2962:Capability: KVM_CAP_SIGNAL_MSI 2963:Architectures: x86 arm64 2964:Type: vm ioctl 2965:Parameters: struct kvm_msi (in) 2966:Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error 2967 2968Directly inject a MSI message. Only valid with in-kernel irqchip that handles 2969MSI messages. 2970 2971:: 2972 2973 struct kvm_msi { 2974 __u32 address_lo; 2975 __u32 address_hi; 2976 __u32 data; 2977 __u32 flags; 2978 __u32 devid; 2979 __u8 pad[12]; 2980 }; 2981 2982flags: 2983 KVM_MSI_VALID_DEVID: devid contains a valid value. The per-VM 2984 KVM_CAP_MSI_DEVID capability advertises the requirement to provide 2985 the device ID. If this capability is not available, userspace 2986 should never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail. 2987 2988If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier 2989for the device that wrote the MSI message. For PCI, this is usually a 2990BDF identifier in the lower 16 bits. 2991 2992On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS 2993feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled, 2994address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of 2995address_hi must be zero. 2996 2997 29984.71 KVM_CREATE_PIT2 2999-------------------- 3000 3001:Capability: KVM_CAP_PIT2 3002:Architectures: x86 3003:Type: vm ioctl 3004:Parameters: struct kvm_pit_config (in) 3005:Returns: 0 on success, -1 on error 3006 3007Creates an in-kernel device model for the i8254 PIT. This call is only valid 3008after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following 3009parameters have to be passed:: 3010 3011 struct kvm_pit_config { 3012 __u32 flags; 3013 __u32 pad[15]; 3014 }; 3015 3016Valid flags are:: 3017 3018 #define KVM_PIT_SPEAKER_DUMMY 1 /* emulate speaker port stub */ 3019 3020PIT timer interrupts may use a per-VM kernel thread for injection. If it 3021exists, this thread will have a name of the following pattern:: 3022 3023 kvm-pit/<owner-process-pid> 3024 3025When running a guest with elevated priorities, the scheduling parameters of 3026this thread may have to be adjusted accordingly. 3027 3028This IOCTL replaces the obsolete KVM_CREATE_PIT. 3029 3030 30314.72 KVM_GET_PIT2 3032----------------- 3033 3034:Capability: KVM_CAP_PIT_STATE2 3035:Architectures: x86 3036:Type: vm ioctl 3037:Parameters: struct kvm_pit_state2 (out) 3038:Returns: 0 on success, -1 on error 3039 3040Retrieves the state of the in-kernel PIT model. Only valid after 3041KVM_CREATE_PIT2. The state is returned in the following structure:: 3042 3043 struct kvm_pit_state2 { 3044 struct kvm_pit_channel_state channels[3]; 3045 __u32 flags; 3046 __u32 reserved[9]; 3047 }; 3048 3049Valid flags are:: 3050 3051 /* disable PIT in HPET legacy mode */ 3052 #define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001 3053 /* speaker port data bit enabled */ 3054 #define KVM_PIT_FLAGS_SPEAKER_DATA_ON 0x00000002 3055 3056This IOCTL replaces the obsolete KVM_GET_PIT. 3057 3058 30594.73 KVM_SET_PIT2 3060----------------- 3061 3062:Capability: KVM_CAP_PIT_STATE2 3063:Architectures: x86 3064:Type: vm ioctl 3065:Parameters: struct kvm_pit_state2 (in) 3066:Returns: 0 on success, -1 on error 3067 3068Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2. 3069See KVM_GET_PIT2 for details on struct kvm_pit_state2. 3070 3071This IOCTL replaces the obsolete KVM_SET_PIT. 3072 3073 30744.74 KVM_PPC_GET_SMMU_INFO 3075-------------------------- 3076 3077:Capability: KVM_CAP_PPC_GET_SMMU_INFO 3078:Architectures: powerpc 3079:Type: vm ioctl 3080:Parameters: None 3081:Returns: 0 on success, -1 on error 3082 3083This populates and returns a structure describing the features of 3084the "Server" class MMU emulation supported by KVM. 3085This can in turn be used by userspace to generate the appropriate 3086device-tree properties for the guest operating system. 3087 3088The structure contains some global information, followed by an 3089array of supported segment page sizes:: 3090 3091 struct kvm_ppc_smmu_info { 3092 __u64 flags; 3093 __u32 slb_size; 3094 __u32 pad; 3095 struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; 3096 }; 3097 3098The supported flags are: 3099 3100 - KVM_PPC_PAGE_SIZES_REAL: 3101 When that flag is set, guest page sizes must "fit" the backing 3102 store page sizes. When not set, any page size in the list can 3103 be used regardless of how they are backed by userspace. 3104 3105 - KVM_PPC_1T_SEGMENTS 3106 The emulated MMU supports 1T segments in addition to the 3107 standard 256M ones. 3108 3109 - KVM_PPC_NO_HASH 3110 This flag indicates that HPT guests are not supported by KVM, 3111 thus all guests must use radix MMU mode. 3112 3113The "slb_size" field indicates how many SLB entries are supported 3114 3115The "sps" array contains 8 entries indicating the supported base 3116page sizes for a segment in increasing order. Each entry is defined 3117as follow:: 3118 3119 struct kvm_ppc_one_seg_page_size { 3120 __u32 page_shift; /* Base page shift of segment (or 0) */ 3121 __u32 slb_enc; /* SLB encoding for BookS */ 3122 struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; 3123 }; 3124 3125An entry with a "page_shift" of 0 is unused. Because the array is 3126organized in increasing order, a lookup can stop when encountering 3127such an entry. 3128 3129The "slb_enc" field provides the encoding to use in the SLB for the 3130page size. The bits are in positions such as the value can directly 3131be OR'ed into the "vsid" argument of the slbmte instruction. 3132 3133The "enc" array is a list which for each of those segment base page 3134size provides the list of supported actual page sizes (which can be 3135only larger or equal to the base page size), along with the 3136corresponding encoding in the hash PTE. Similarly, the array is 31378 entries sorted by increasing sizes and an entry with a "0" shift 3138is an empty entry and a terminator:: 3139 3140 struct kvm_ppc_one_page_size { 3141 __u32 page_shift; /* Page shift (or 0) */ 3142 __u32 pte_enc; /* Encoding in the HPTE (>>12) */ 3143 }; 3144 3145The "pte_enc" field provides a value that can OR'ed into the hash 3146PTE's RPN field (ie, it needs to be shifted left by 12 to OR it 3147into the hash PTE second double word). 3148 31494.75 KVM_IRQFD 3150-------------- 3151 3152:Capability: KVM_CAP_IRQFD 3153:Architectures: x86 s390 arm64 3154:Type: vm ioctl 3155:Parameters: struct kvm_irqfd (in) 3156:Returns: 0 on success, -1 on error 3157 3158Allows setting an eventfd to directly trigger a guest interrupt. 3159kvm_irqfd.fd specifies the file descriptor to use as the eventfd and 3160kvm_irqfd.gsi specifies the irqchip pin toggled by this event. When 3161an event is triggered on the eventfd, an interrupt is injected into 3162the guest using the specified gsi pin. The irqfd is removed using 3163the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd 3164and kvm_irqfd.gsi. 3165 3166With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD supports a de-assert and notify 3167mechanism allowing emulation of level-triggered, irqfd-based 3168interrupts. When KVM_IRQFD_FLAG_RESAMPLE is set the user must pass an 3169additional eventfd in the kvm_irqfd.resamplefd field. When operating 3170in resample mode, posting of an interrupt through kvm_irq.fd asserts 3171the specified gsi in the irqchip. When the irqchip is resampled, such 3172as from an EOI, the gsi is de-asserted and the user is notified via 3173kvm_irqfd.resamplefd. It is the user's responsibility to re-queue 3174the interrupt if the device making use of it still requires service. 3175Note that closing the resamplefd is not sufficient to disable the 3176irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment 3177and need not be specified with KVM_IRQFD_FLAG_DEASSIGN. 3178 3179On arm64, gsi routing being supported, the following can happen: 3180 3181- in case no routing entry is associated to this gsi, injection fails 3182- in case the gsi is associated to an irqchip routing entry, 3183 irqchip.pin + 32 corresponds to the injected SPI ID. 3184- in case the gsi is associated to an MSI routing entry, the MSI 3185 message and device ID are translated into an LPI (support restricted 3186 to GICv3 ITS in-kernel emulation). 3187 31884.76 KVM_PPC_ALLOCATE_HTAB 3189-------------------------- 3190 3191:Capability: KVM_CAP_PPC_ALLOC_HTAB 3192:Architectures: powerpc 3193:Type: vm ioctl 3194:Parameters: Pointer to u32 containing hash table order (in/out) 3195:Returns: 0 on success, -1 on error 3196 3197This requests the host kernel to allocate an MMU hash table for a 3198guest using the PAPR paravirtualization interface. This only does 3199anything if the kernel is configured to use the Book 3S HV style of 3200virtualization. Otherwise the capability doesn't exist and the ioctl 3201returns an ENOTTY error. The rest of this description assumes Book 3S 3202HV. 3203 3204There must be no vcpus running when this ioctl is called; if there 3205are, it will do nothing and return an EBUSY error. 3206 3207The parameter is a pointer to a 32-bit unsigned integer variable 3208containing the order (log base 2) of the desired size of the hash 3209table, which must be between 18 and 46. On successful return from the 3210ioctl, the value will not be changed by the kernel. 3211 3212If no hash table has been allocated when any vcpu is asked to run 3213(with the KVM_RUN ioctl), the host kernel will allocate a 3214default-sized hash table (16 MB). 3215 3216If this ioctl is called when a hash table has already been allocated, 3217with a different order from the existing hash table, the existing hash 3218table will be freed and a new one allocated. If this is ioctl is 3219called when a hash table has already been allocated of the same order 3220as specified, the kernel will clear out the existing hash table (zero 3221all HPTEs). In either case, if the guest is using the virtualized 3222real-mode area (VRMA) facility, the kernel will re-create the VMRA 3223HPTEs on the next KVM_RUN of any vcpu. 3224 32254.77 KVM_S390_INTERRUPT 3226----------------------- 3227 3228:Capability: basic 3229:Architectures: s390 3230:Type: vm ioctl, vcpu ioctl 3231:Parameters: struct kvm_s390_interrupt (in) 3232:Returns: 0 on success, -1 on error 3233 3234Allows to inject an interrupt to the guest. Interrupts can be floating 3235(vm ioctl) or per cpu (vcpu ioctl), depending on the interrupt type. 3236 3237Interrupt parameters are passed via kvm_s390_interrupt:: 3238 3239 struct kvm_s390_interrupt { 3240 __u32 type; 3241 __u32 parm; 3242 __u64 parm64; 3243 }; 3244 3245type can be one of the following: 3246 3247KVM_S390_SIGP_STOP (vcpu) 3248 - sigp stop; optional flags in parm 3249KVM_S390_PROGRAM_INT (vcpu) 3250 - program check; code in parm 3251KVM_S390_SIGP_SET_PREFIX (vcpu) 3252 - sigp set prefix; prefix address in parm 3253KVM_S390_RESTART (vcpu) 3254 - restart 3255KVM_S390_INT_CLOCK_COMP (vcpu) 3256 - clock comparator interrupt 3257KVM_S390_INT_CPU_TIMER (vcpu) 3258 - CPU timer interrupt 3259KVM_S390_INT_VIRTIO (vm) 3260 - virtio external interrupt; external interrupt 3261 parameters in parm and parm64 3262KVM_S390_INT_SERVICE (vm) 3263 - sclp external interrupt; sclp parameter in parm 3264KVM_S390_INT_EMERGENCY (vcpu) 3265 - sigp emergency; source cpu in parm 3266KVM_S390_INT_EXTERNAL_CALL (vcpu) 3267 - sigp external call; source cpu in parm 3268KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) 3269 - compound value to indicate an 3270 I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel); 3271 I/O interruption parameters in parm (subchannel) and parm64 (intparm, 3272 interruption subclass) 3273KVM_S390_MCHK (vm, vcpu) 3274 - machine check interrupt; cr 14 bits in parm, machine check interrupt 3275 code in parm64 (note that machine checks needing further payload are not 3276 supported by this ioctl) 3277 3278This is an asynchronous vcpu ioctl and can be invoked from any thread. 3279 32804.78 KVM_PPC_GET_HTAB_FD 3281------------------------ 3282 3283:Capability: KVM_CAP_PPC_HTAB_FD 3284:Architectures: powerpc 3285:Type: vm ioctl 3286:Parameters: Pointer to struct kvm_get_htab_fd (in) 3287:Returns: file descriptor number (>= 0) on success, -1 on error 3288 3289This returns a file descriptor that can be used either to read out the 3290entries in the guest's hashed page table (HPT), or to write entries to 3291initialize the HPT. The returned fd can only be written to if the 3292KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and 3293can only be read if that bit is clear. The argument struct looks like 3294this:: 3295 3296 /* For KVM_PPC_GET_HTAB_FD */ 3297 struct kvm_get_htab_fd { 3298 __u64 flags; 3299 __u64 start_index; 3300 __u64 reserved[2]; 3301 }; 3302 3303 /* Values for kvm_get_htab_fd.flags */ 3304 #define KVM_GET_HTAB_BOLTED_ONLY ((__u64)0x1) 3305 #define KVM_GET_HTAB_WRITE ((__u64)0x2) 3306 3307The 'start_index' field gives the index in the HPT of the entry at 3308which to start reading. It is ignored when writing. 3309 3310Reads on the fd will initially supply information about all 3311"interesting" HPT entries. Interesting entries are those with the 3312bolted bit set, if the KVM_GET_HTAB_BOLTED_ONLY bit is set, otherwise 3313all entries. When the end of the HPT is reached, the read() will 3314return. If read() is called again on the fd, it will start again from 3315the beginning of the HPT, but will only return HPT entries that have 3316changed since they were last read. 3317 3318Data read or written is structured as a header (8 bytes) followed by a 3319series of valid HPT entries (16 bytes) each. The header indicates how 3320many valid HPT entries there are and how many invalid entries follow 3321the valid entries. The invalid entries are not represented explicitly 3322in the stream. The header format is:: 3323 3324 struct kvm_get_htab_header { 3325 __u32 index; 3326 __u16 n_valid; 3327 __u16 n_invalid; 3328 }; 3329 3330Writes to the fd create HPT entries starting at the index given in the 3331header; first 'n_valid' valid entries with contents from the data 3332written, then 'n_invalid' invalid entries, invalidating any previously 3333valid entries found. 3334 33354.79 KVM_CREATE_DEVICE 3336---------------------- 3337 3338:Capability: KVM_CAP_DEVICE_CTRL 3339:Architectures: all 3340:Type: vm ioctl 3341:Parameters: struct kvm_create_device (in/out) 3342:Returns: 0 on success, -1 on error 3343 3344Errors: 3345 3346 ====== ======================================================= 3347 ENODEV The device type is unknown or unsupported 3348 EEXIST Device already created, and this type of device may not 3349 be instantiated multiple times 3350 ====== ======================================================= 3351 3352 Other error conditions may be defined by individual device types or 3353 have their standard meanings. 3354 3355Creates an emulated device in the kernel. The file descriptor returned 3356in fd can be used with KVM_SET/GET/HAS_DEVICE_ATTR. 3357 3358If the KVM_CREATE_DEVICE_TEST flag is set, only test whether the 3359device type is supported (not necessarily whether it can be created 3360in the current vm). 3361 3362Individual devices should not define flags. Attributes should be used 3363for specifying any behavior that is not implied by the device type 3364number. 3365 3366:: 3367 3368 struct kvm_create_device { 3369 __u32 type; /* in: KVM_DEV_TYPE_xxx */ 3370 __u32 fd; /* out: device handle */ 3371 __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */ 3372 }; 3373 33744.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR 3375-------------------------------------------- 3376 3377:Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, 3378 KVM_CAP_VCPU_ATTRIBUTES for vcpu device 3379 KVM_CAP_SYS_ATTRIBUTES for system (/dev/kvm) device (no set) 3380:Architectures: x86, arm64, s390 3381:Type: device ioctl, vm ioctl, vcpu ioctl 3382:Parameters: struct kvm_device_attr 3383:Returns: 0 on success, -1 on error 3384 3385Errors: 3386 3387 ===== ============================================================= 3388 ENXIO The group or attribute is unknown/unsupported for this device 3389 or hardware support is missing. 3390 EPERM The attribute cannot (currently) be accessed this way 3391 (e.g. read-only attribute, or attribute that only makes 3392 sense when the device is in a different state) 3393 ===== ============================================================= 3394 3395 Other error conditions may be defined by individual device types. 3396 3397Gets/sets a specified piece of device configuration and/or state. The 3398semantics are device-specific. See individual device documentation in 3399the "devices" directory. As with ONE_REG, the size of the data 3400transferred is defined by the particular attribute. 3401 3402:: 3403 3404 struct kvm_device_attr { 3405 __u32 flags; /* no flags currently defined */ 3406 __u32 group; /* device-defined */ 3407 __u64 attr; /* group-defined */ 3408 __u64 addr; /* userspace address of attr data */ 3409 }; 3410 34114.81 KVM_HAS_DEVICE_ATTR 3412------------------------ 3413 3414:Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, 3415 KVM_CAP_VCPU_ATTRIBUTES for vcpu device 3416 KVM_CAP_SYS_ATTRIBUTES for system (/dev/kvm) device 3417:Type: device ioctl, vm ioctl, vcpu ioctl 3418:Parameters: struct kvm_device_attr 3419:Returns: 0 on success, -1 on error 3420 3421Errors: 3422 3423 ===== ============================================================= 3424 ENXIO The group or attribute is unknown/unsupported for this device 3425 or hardware support is missing. 3426 ===== ============================================================= 3427 3428Tests whether a device supports a particular attribute. A successful 3429return indicates the attribute is implemented. It does not necessarily 3430indicate that the attribute can be read or written in the device's 3431current state. "addr" is ignored. 3432 3433.. _KVM_ARM_VCPU_INIT: 3434 34354.82 KVM_ARM_VCPU_INIT 3436---------------------- 3437 3438:Capability: basic 3439:Architectures: arm64 3440:Type: vcpu ioctl 3441:Parameters: struct kvm_vcpu_init (in) 3442:Returns: 0 on success; -1 on error 3443 3444Errors: 3445 3446 ====== ================================================================= 3447 EINVAL the target is unknown, or the combination of features is invalid. 3448 ENOENT a features bit specified is unknown. 3449 ====== ================================================================= 3450 3451This tells KVM what type of CPU to present to the guest, and what 3452optional features it should have. This will cause a reset of the cpu 3453registers to their initial values. If this is not called, KVM_RUN will 3454return ENOEXEC for that vcpu. 3455 3456The initial values are defined as: 3457 - Processor state: 3458 * AArch64: EL1h, D, A, I and F bits set. All other bits 3459 are cleared. 3460 * AArch32: SVC, A, I and F bits set. All other bits are 3461 cleared. 3462 - General Purpose registers, including PC and SP: set to 0 3463 - FPSIMD/NEON registers: set to 0 3464 - SVE registers: set to 0 3465 - System registers: Reset to their architecturally defined 3466 values as for a warm reset to EL1 (resp. SVC) 3467 3468Note that because some registers reflect machine topology, all vcpus 3469should be created before this ioctl is invoked. 3470 3471Userspace can call this function multiple times for a given vcpu, including 3472after the vcpu has been run. This will reset the vcpu to its initial 3473state. All calls to this function after the initial call must use the same 3474target and same set of feature flags, otherwise EINVAL will be returned. 3475 3476Possible features: 3477 3478 - KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state. 3479 Depends on KVM_CAP_ARM_PSCI. If not set, the CPU will be powered on 3480 and execute guest code when KVM_RUN is called. 3481 - KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode. 3482 Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only). 3483 - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 (or a future revision 3484 backward compatible with v0.2) for the CPU. 3485 Depends on KVM_CAP_ARM_PSCI_0_2. 3486 - KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU. 3487 Depends on KVM_CAP_ARM_PMU_V3. 3488 3489 - KVM_ARM_VCPU_PTRAUTH_ADDRESS: Enables Address Pointer authentication 3490 for arm64 only. 3491 Depends on KVM_CAP_ARM_PTRAUTH_ADDRESS. 3492 If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are 3493 both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and 3494 KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be 3495 requested. 3496 3497 - KVM_ARM_VCPU_PTRAUTH_GENERIC: Enables Generic Pointer authentication 3498 for arm64 only. 3499 Depends on KVM_CAP_ARM_PTRAUTH_GENERIC. 3500 If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are 3501 both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and 3502 KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be 3503 requested. 3504 3505 - KVM_ARM_VCPU_SVE: Enables SVE for the CPU (arm64 only). 3506 Depends on KVM_CAP_ARM_SVE. 3507 Requires KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE): 3508 3509 * After KVM_ARM_VCPU_INIT: 3510 3511 - KVM_REG_ARM64_SVE_VLS may be read using KVM_GET_ONE_REG: the 3512 initial value of this pseudo-register indicates the best set of 3513 vector lengths possible for a vcpu on this host. 3514 3515 * Before KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE): 3516 3517 - KVM_RUN and KVM_GET_REG_LIST are not available; 3518 3519 - KVM_GET_ONE_REG and KVM_SET_ONE_REG cannot be used to access 3520 the scalable architectural SVE registers 3521 KVM_REG_ARM64_SVE_ZREG(), KVM_REG_ARM64_SVE_PREG() or 3522 KVM_REG_ARM64_SVE_FFR; 3523 3524 - KVM_REG_ARM64_SVE_VLS may optionally be written using 3525 KVM_SET_ONE_REG, to modify the set of vector lengths available 3526 for the vcpu. 3527 3528 * After KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE): 3529 3530 - the KVM_REG_ARM64_SVE_VLS pseudo-register is immutable, and can 3531 no longer be written using KVM_SET_ONE_REG. 3532 35334.83 KVM_ARM_PREFERRED_TARGET 3534----------------------------- 3535 3536:Capability: basic 3537:Architectures: arm64 3538:Type: vm ioctl 3539:Parameters: struct kvm_vcpu_init (out) 3540:Returns: 0 on success; -1 on error 3541 3542Errors: 3543 3544 ====== ========================================== 3545 ENODEV no preferred target available for the host 3546 ====== ========================================== 3547 3548This queries KVM for preferred CPU target type which can be emulated 3549by KVM on underlying host. 3550 3551The ioctl returns struct kvm_vcpu_init instance containing information 3552about preferred CPU target type and recommended features for it. The 3553kvm_vcpu_init->features bitmap returned will have feature bits set if 3554the preferred target recommends setting these features, but this is 3555not mandatory. 3556 3557The information returned by this ioctl can be used to prepare an instance 3558of struct kvm_vcpu_init for KVM_ARM_VCPU_INIT ioctl which will result in 3559VCPU matching underlying host. 3560 3561 35624.84 KVM_GET_REG_LIST 3563--------------------- 3564 3565:Capability: basic 3566:Architectures: arm64, mips, riscv 3567:Type: vcpu ioctl 3568:Parameters: struct kvm_reg_list (in/out) 3569:Returns: 0 on success; -1 on error 3570 3571Errors: 3572 3573 ===== ============================================================== 3574 E2BIG the reg index list is too big to fit in the array specified by 3575 the user (the number required will be written into n). 3576 ===== ============================================================== 3577 3578:: 3579 3580 struct kvm_reg_list { 3581 __u64 n; /* number of registers in reg[] */ 3582 __u64 reg[0]; 3583 }; 3584 3585This ioctl returns the guest registers that are supported for the 3586KVM_GET_ONE_REG/KVM_SET_ONE_REG calls. 3587 3588Note that s390 does not support KVM_GET_REG_LIST for historical reasons 3589(read: nobody cared). The set of registers in kernels 4.x and newer is: 3590 3591- KVM_REG_S390_TODPR 3592 3593- KVM_REG_S390_EPOCHDIFF 3594 3595- KVM_REG_S390_CPU_TIMER 3596 3597- KVM_REG_S390_CLOCK_COMP 3598 3599- KVM_REG_S390_PFTOKEN 3600 3601- KVM_REG_S390_PFCOMPARE 3602 3603- KVM_REG_S390_PFSELECT 3604 3605- KVM_REG_S390_PP 3606 3607- KVM_REG_S390_GBEA 3608 3609 36104.85 KVM_ARM_SET_DEVICE_ADDR (deprecated) 3611----------------------------------------- 3612 3613:Capability: KVM_CAP_ARM_SET_DEVICE_ADDR 3614:Architectures: arm64 3615:Type: vm ioctl 3616:Parameters: struct kvm_arm_device_address (in) 3617:Returns: 0 on success, -1 on error 3618 3619Errors: 3620 3621 ====== ============================================ 3622 ENODEV The device id is unknown 3623 ENXIO Device not supported on current system 3624 EEXIST Address already set 3625 E2BIG Address outside guest physical address space 3626 EBUSY Address overlaps with other device range 3627 ====== ============================================ 3628 3629:: 3630 3631 struct kvm_arm_device_addr { 3632 __u64 id; 3633 __u64 addr; 3634 }; 3635 3636Specify a device address in the guest's physical address space where guests 3637can access emulated or directly exposed devices, which the host kernel needs 3638to know about. The id field is an architecture specific identifier for a 3639specific device. 3640 3641arm64 divides the id field into two parts, a device id and an 3642address type id specific to the individual device:: 3643 3644 bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 | 3645 field: | 0x00000000 | device id | addr type id | 3646 3647arm64 currently only require this when using the in-kernel GIC 3648support for the hardware VGIC features, using KVM_ARM_DEVICE_VGIC_V2 3649as the device id. When setting the base address for the guest's 3650mapping of the VGIC virtual CPU and distributor interface, the ioctl 3651must be called after calling KVM_CREATE_IRQCHIP, but before calling 3652KVM_RUN on any of the VCPUs. Calling this ioctl twice for any of the 3653base addresses will return -EEXIST. 3654 3655Note, this IOCTL is deprecated and the more flexible SET/GET_DEVICE_ATTR API 3656should be used instead. 3657 3658 36594.86 KVM_PPC_RTAS_DEFINE_TOKEN 3660------------------------------ 3661 3662:Capability: KVM_CAP_PPC_RTAS 3663:Architectures: ppc 3664:Type: vm ioctl 3665:Parameters: struct kvm_rtas_token_args 3666:Returns: 0 on success, -1 on error 3667 3668Defines a token value for a RTAS (Run Time Abstraction Services) 3669service in order to allow it to be handled in the kernel. The 3670argument struct gives the name of the service, which must be the name 3671of a service that has a kernel-side implementation. If the token 3672value is non-zero, it will be associated with that service, and 3673subsequent RTAS calls by the guest specifying that token will be 3674handled by the kernel. If the token value is 0, then any token 3675associated with the service will be forgotten, and subsequent RTAS 3676calls by the guest for that service will be passed to userspace to be 3677handled. 3678 36794.87 KVM_SET_GUEST_DEBUG 3680------------------------ 3681 3682:Capability: KVM_CAP_SET_GUEST_DEBUG 3683:Architectures: x86, s390, ppc, arm64 3684:Type: vcpu ioctl 3685:Parameters: struct kvm_guest_debug (in) 3686:Returns: 0 on success; -1 on error 3687 3688:: 3689 3690 struct kvm_guest_debug { 3691 __u32 control; 3692 __u32 pad; 3693 struct kvm_guest_debug_arch arch; 3694 }; 3695 3696Set up the processor specific debug registers and configure vcpu for 3697handling guest debug events. There are two parts to the structure, the 3698first a control bitfield indicates the type of debug events to handle 3699when running. Common control bits are: 3700 3701 - KVM_GUESTDBG_ENABLE: guest debugging is enabled 3702 - KVM_GUESTDBG_SINGLESTEP: the next run should single-step 3703 3704The top 16 bits of the control field are architecture specific control 3705flags which can include the following: 3706 3707 - KVM_GUESTDBG_USE_SW_BP: using software breakpoints [x86, arm64] 3708 - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390] 3709 - KVM_GUESTDBG_USE_HW: using hardware debug events [arm64] 3710 - KVM_GUESTDBG_INJECT_DB: inject DB type exception [x86] 3711 - KVM_GUESTDBG_INJECT_BP: inject BP type exception [x86] 3712 - KVM_GUESTDBG_EXIT_PENDING: trigger an immediate guest exit [s390] 3713 - KVM_GUESTDBG_BLOCKIRQ: avoid injecting interrupts/NMI/SMI [x86] 3714 3715For example KVM_GUESTDBG_USE_SW_BP indicates that software breakpoints 3716are enabled in memory so we need to ensure breakpoint exceptions are 3717correctly trapped and the KVM run loop exits at the breakpoint and not 3718running off into the normal guest vector. For KVM_GUESTDBG_USE_HW_BP 3719we need to ensure the guest vCPUs architecture specific registers are 3720updated to the correct (supplied) values. 3721 3722The second part of the structure is architecture specific and 3723typically contains a set of debug registers. 3724 3725For arm64 the number of debug registers is implementation defined and 3726can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and 3727KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number 3728indicating the number of supported registers. 3729 3730For ppc, the KVM_CAP_PPC_GUEST_DEBUG_SSTEP capability indicates whether 3731the single-step debug event (KVM_GUESTDBG_SINGLESTEP) is supported. 3732 3733Also when supported, KVM_CAP_SET_GUEST_DEBUG2 capability indicates the 3734supported KVM_GUESTDBG_* bits in the control field. 3735 3736When debug events exit the main run loop with the reason 3737KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run 3738structure containing architecture specific debug information. 3739 37404.88 KVM_GET_EMULATED_CPUID 3741--------------------------- 3742 3743:Capability: KVM_CAP_EXT_EMUL_CPUID 3744:Architectures: x86 3745:Type: system ioctl 3746:Parameters: struct kvm_cpuid2 (in/out) 3747:Returns: 0 on success, -1 on error 3748 3749:: 3750 3751 struct kvm_cpuid2 { 3752 __u32 nent; 3753 __u32 flags; 3754 struct kvm_cpuid_entry2 entries[0]; 3755 }; 3756 3757The member 'flags' is used for passing flags from userspace. 3758 3759:: 3760 3761 #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) 3762 #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) /* deprecated */ 3763 #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) /* deprecated */ 3764 3765 struct kvm_cpuid_entry2 { 3766 __u32 function; 3767 __u32 index; 3768 __u32 flags; 3769 __u32 eax; 3770 __u32 ebx; 3771 __u32 ecx; 3772 __u32 edx; 3773 __u32 padding[3]; 3774 }; 3775 3776This ioctl returns x86 cpuid features which are emulated by 3777kvm.Userspace can use the information returned by this ioctl to query 3778which features are emulated by kvm instead of being present natively. 3779 3780Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2 3781structure with the 'nent' field indicating the number of entries in 3782the variable-size array 'entries'. If the number of entries is too low 3783to describe the cpu capabilities, an error (E2BIG) is returned. If the 3784number is too high, the 'nent' field is adjusted and an error (ENOMEM) 3785is returned. If the number is just right, the 'nent' field is adjusted 3786to the number of valid entries in the 'entries' array, which is then 3787filled. 3788 3789The entries returned are the set CPUID bits of the respective features 3790which kvm emulates, as returned by the CPUID instruction, with unknown 3791or unsupported feature bits cleared. 3792 3793Features like x2apic, for example, may not be present in the host cpu 3794but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be 3795emulated efficiently and thus not included here. 3796 3797The fields in each entry are defined as follows: 3798 3799 function: 3800 the eax value used to obtain the entry 3801 index: 3802 the ecx value used to obtain the entry (for entries that are 3803 affected by ecx) 3804 flags: 3805 an OR of zero or more of the following: 3806 3807 KVM_CPUID_FLAG_SIGNIFCANT_INDEX: 3808 if the index field is valid 3809 3810 eax, ebx, ecx, edx: 3811 3812 the values returned by the cpuid instruction for 3813 this function/index combination 3814 38154.89 KVM_S390_MEM_OP 3816-------------------- 3817 3818:Capability: KVM_CAP_S390_MEM_OP, KVM_CAP_S390_PROTECTED, KVM_CAP_S390_MEM_OP_EXTENSION 3819:Architectures: s390 3820:Type: vm ioctl, vcpu ioctl 3821:Parameters: struct kvm_s390_mem_op (in) 3822:Returns: = 0 on success, 3823 < 0 on generic error (e.g. -EFAULT or -ENOMEM), 3824 16 bit program exception code if the access causes such an exception 3825 3826Read or write data from/to the VM's memory. 3827The KVM_CAP_S390_MEM_OP_EXTENSION capability specifies what functionality is 3828supported. 3829 3830Parameters are specified via the following structure:: 3831 3832 struct kvm_s390_mem_op { 3833 __u64 gaddr; /* the guest address */ 3834 __u64 flags; /* flags */ 3835 __u32 size; /* amount of bytes */ 3836 __u32 op; /* type of operation */ 3837 __u64 buf; /* buffer in userspace */ 3838 union { 3839 struct { 3840 __u8 ar; /* the access register number */ 3841 __u8 key; /* access key, ignored if flag unset */ 3842 __u8 pad1[6]; /* ignored */ 3843 __u64 old_addr; /* ignored if flag unset */ 3844 }; 3845 __u32 sida_offset; /* offset into the sida */ 3846 __u8 reserved[32]; /* ignored */ 3847 }; 3848 }; 3849 3850The start address of the memory region has to be specified in the "gaddr" 3851field, and the length of the region in the "size" field (which must not 3852be 0). The maximum value for "size" can be obtained by checking the 3853KVM_CAP_S390_MEM_OP capability. "buf" is the buffer supplied by the 3854userspace application where the read data should be written to for 3855a read access, or where the data that should be written is stored for 3856a write access. The "reserved" field is meant for future extensions. 3857Reserved and unused values are ignored. Future extension that add members must 3858introduce new flags. 3859 3860The type of operation is specified in the "op" field. Flags modifying 3861their behavior can be set in the "flags" field. Undefined flag bits must 3862be set to 0. 3863 3864Possible operations are: 3865 * ``KVM_S390_MEMOP_LOGICAL_READ`` 3866 * ``KVM_S390_MEMOP_LOGICAL_WRITE`` 3867 * ``KVM_S390_MEMOP_ABSOLUTE_READ`` 3868 * ``KVM_S390_MEMOP_ABSOLUTE_WRITE`` 3869 * ``KVM_S390_MEMOP_SIDA_READ`` 3870 * ``KVM_S390_MEMOP_SIDA_WRITE`` 3871 * ``KVM_S390_MEMOP_ABSOLUTE_CMPXCHG`` 3872 3873Logical read/write: 3874^^^^^^^^^^^^^^^^^^^ 3875 3876Access logical memory, i.e. translate the given guest address to an absolute 3877address given the state of the VCPU and use the absolute address as target of 3878the access. "ar" designates the access register number to be used; the valid 3879range is 0..15. 3880Logical accesses are permitted for the VCPU ioctl only. 3881Logical accesses are permitted for non-protected guests only. 3882 3883Supported flags: 3884 * ``KVM_S390_MEMOP_F_CHECK_ONLY`` 3885 * ``KVM_S390_MEMOP_F_INJECT_EXCEPTION`` 3886 * ``KVM_S390_MEMOP_F_SKEY_PROTECTION`` 3887 3888The KVM_S390_MEMOP_F_CHECK_ONLY flag can be set to check whether the 3889corresponding memory access would cause an access exception; however, 3890no actual access to the data in memory at the destination is performed. 3891In this case, "buf" is unused and can be NULL. 3892 3893In case an access exception occurred during the access (or would occur 3894in case of KVM_S390_MEMOP_F_CHECK_ONLY), the ioctl returns a positive 3895error number indicating the type of exception. This exception is also 3896raised directly at the corresponding VCPU if the flag 3897KVM_S390_MEMOP_F_INJECT_EXCEPTION is set. 3898On protection exceptions, unless specified otherwise, the injected 3899translation-exception identifier (TEID) indicates suppression. 3900 3901If the KVM_S390_MEMOP_F_SKEY_PROTECTION flag is set, storage key 3902protection is also in effect and may cause exceptions if accesses are 3903prohibited given the access key designated by "key"; the valid range is 0..15. 3904KVM_S390_MEMOP_F_SKEY_PROTECTION is available if KVM_CAP_S390_MEM_OP_EXTENSION 3905is > 0. 3906Since the accessed memory may span multiple pages and those pages might have 3907different storage keys, it is possible that a protection exception occurs 3908after memory has been modified. In this case, if the exception is injected, 3909the TEID does not indicate suppression. 3910 3911Absolute read/write: 3912^^^^^^^^^^^^^^^^^^^^ 3913 3914Access absolute memory. This operation is intended to be used with the 3915KVM_S390_MEMOP_F_SKEY_PROTECTION flag, to allow accessing memory and performing 3916the checks required for storage key protection as one operation (as opposed to 3917user space getting the storage keys, performing the checks, and accessing 3918memory thereafter, which could lead to a delay between check and access). 3919Absolute accesses are permitted for the VM ioctl if KVM_CAP_S390_MEM_OP_EXTENSION 3920has the KVM_S390_MEMOP_EXTENSION_CAP_BASE bit set. 3921Currently absolute accesses are not permitted for VCPU ioctls. 3922Absolute accesses are permitted for non-protected guests only. 3923 3924Supported flags: 3925 * ``KVM_S390_MEMOP_F_CHECK_ONLY`` 3926 * ``KVM_S390_MEMOP_F_SKEY_PROTECTION`` 3927 3928The semantics of the flags common with logical accesses are as for logical 3929accesses. 3930 3931Absolute cmpxchg: 3932^^^^^^^^^^^^^^^^^ 3933 3934Perform cmpxchg on absolute guest memory. Intended for use with the 3935KVM_S390_MEMOP_F_SKEY_PROTECTION flag. 3936Instead of doing an unconditional write, the access occurs only if the target 3937location contains the value pointed to by "old_addr". 3938This is performed as an atomic cmpxchg with the length specified by the "size" 3939parameter. "size" must be a power of two up to and including 16. 3940If the exchange did not take place because the target value doesn't match the 3941old value, the value "old_addr" points to is replaced by the target value. 3942User space can tell if an exchange took place by checking if this replacement 3943occurred. The cmpxchg op is permitted for the VM ioctl if 3944KVM_CAP_S390_MEM_OP_EXTENSION has flag KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG set. 3945 3946Supported flags: 3947 * ``KVM_S390_MEMOP_F_SKEY_PROTECTION`` 3948 3949SIDA read/write: 3950^^^^^^^^^^^^^^^^ 3951 3952Access the secure instruction data area which contains memory operands necessary 3953for instruction emulation for protected guests. 3954SIDA accesses are available if the KVM_CAP_S390_PROTECTED capability is available. 3955SIDA accesses are permitted for the VCPU ioctl only. 3956SIDA accesses are permitted for protected guests only. 3957 3958No flags are supported. 3959 39604.90 KVM_S390_GET_SKEYS 3961----------------------- 3962 3963:Capability: KVM_CAP_S390_SKEYS 3964:Architectures: s390 3965:Type: vm ioctl 3966:Parameters: struct kvm_s390_skeys 3967:Returns: 0 on success, KVM_S390_GET_SKEYS_NONE if guest is not using storage 3968 keys, negative value on error 3969 3970This ioctl is used to get guest storage key values on the s390 3971architecture. The ioctl takes parameters via the kvm_s390_skeys struct:: 3972 3973 struct kvm_s390_skeys { 3974 __u64 start_gfn; 3975 __u64 count; 3976 __u64 skeydata_addr; 3977 __u32 flags; 3978 __u32 reserved[9]; 3979 }; 3980 3981The start_gfn field is the number of the first guest frame whose storage keys 3982you want to get. 3983 3984The count field is the number of consecutive frames (starting from start_gfn) 3985whose storage keys to get. The count field must be at least 1 and the maximum 3986allowed value is defined as KVM_S390_SKEYS_MAX. Values outside this range 3987will cause the ioctl to return -EINVAL. 3988 3989The skeydata_addr field is the address to a buffer large enough to hold count 3990bytes. This buffer will be filled with storage key data by the ioctl. 3991 39924.91 KVM_S390_SET_SKEYS 3993----------------------- 3994 3995:Capability: KVM_CAP_S390_SKEYS 3996:Architectures: s390 3997:Type: vm ioctl 3998:Parameters: struct kvm_s390_skeys 3999:Returns: 0 on success, negative value on error 4000 4001This ioctl is used to set guest storage key values on the s390 4002architecture. The ioctl takes parameters via the kvm_s390_skeys struct. 4003See section on KVM_S390_GET_SKEYS for struct definition. 4004 4005The start_gfn field is the number of the first guest frame whose storage keys 4006you want to set. 4007 4008The count field is the number of consecutive frames (starting from start_gfn) 4009whose storage keys to get. The count field must be at least 1 and the maximum 4010allowed value is defined as KVM_S390_SKEYS_MAX. Values outside this range 4011will cause the ioctl to return -EINVAL. 4012 4013The skeydata_addr field is the address to a buffer containing count bytes of 4014storage keys. Each byte in the buffer will be set as the storage key for a 4015single frame starting at start_gfn for count frames. 4016 4017Note: If any architecturally invalid key value is found in the given data then 4018the ioctl will return -EINVAL. 4019 40204.92 KVM_S390_IRQ 4021----------------- 4022 4023:Capability: KVM_CAP_S390_INJECT_IRQ 4024:Architectures: s390 4025:Type: vcpu ioctl 4026:Parameters: struct kvm_s390_irq (in) 4027:Returns: 0 on success, -1 on error 4028 4029Errors: 4030 4031 4032 ====== ================================================================= 4033 EINVAL interrupt type is invalid 4034 type is KVM_S390_SIGP_STOP and flag parameter is invalid value, 4035 type is KVM_S390_INT_EXTERNAL_CALL and code is bigger 4036 than the maximum of VCPUs 4037 EBUSY type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped, 4038 type is KVM_S390_SIGP_STOP and a stop irq is already pending, 4039 type is KVM_S390_INT_EXTERNAL_CALL and an external call interrupt 4040 is already pending 4041 ====== ================================================================= 4042 4043Allows to inject an interrupt to the guest. 4044 4045Using struct kvm_s390_irq as a parameter allows 4046to inject additional payload which is not 4047possible via KVM_S390_INTERRUPT. 4048 4049Interrupt parameters are passed via kvm_s390_irq:: 4050 4051 struct kvm_s390_irq { 4052 __u64 type; 4053 union { 4054 struct kvm_s390_io_info io; 4055 struct kvm_s390_ext_info ext; 4056 struct kvm_s390_pgm_info pgm; 4057 struct kvm_s390_emerg_info emerg; 4058 struct kvm_s390_extcall_info extcall; 4059 struct kvm_s390_prefix_info prefix; 4060 struct kvm_s390_stop_info stop; 4061 struct kvm_s390_mchk_info mchk; 4062 char reserved[64]; 4063 } u; 4064 }; 4065 4066type can be one of the following: 4067 4068- KVM_S390_SIGP_STOP - sigp stop; parameter in .stop 4069- KVM_S390_PROGRAM_INT - program check; parameters in .pgm 4070- KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix 4071- KVM_S390_RESTART - restart; no parameters 4072- KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters 4073- KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters 4074- KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg 4075- KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall 4076- KVM_S390_MCHK - machine check interrupt; parameters in .mchk 4077 4078This is an asynchronous vcpu ioctl and can be invoked from any thread. 4079 40804.94 KVM_S390_GET_IRQ_STATE 4081--------------------------- 4082 4083:Capability: KVM_CAP_S390_IRQ_STATE 4084:Architectures: s390 4085:Type: vcpu ioctl 4086:Parameters: struct kvm_s390_irq_state (out) 4087:Returns: >= number of bytes copied into buffer, 4088 -EINVAL if buffer size is 0, 4089 -ENOBUFS if buffer size is too small to fit all pending interrupts, 4090 -EFAULT if the buffer address was invalid 4091 4092This ioctl allows userspace to retrieve the complete state of all currently 4093pending interrupts in a single buffer. Use cases include migration 4094and introspection. The parameter structure contains the address of a 4095userspace buffer and its length:: 4096 4097 struct kvm_s390_irq_state { 4098 __u64 buf; 4099 __u32 flags; /* will stay unused for compatibility reasons */ 4100 __u32 len; 4101 __u32 reserved[4]; /* will stay unused for compatibility reasons */ 4102 }; 4103 4104Userspace passes in the above struct and for each pending interrupt a 4105struct kvm_s390_irq is copied to the provided buffer. 4106 4107The structure contains a flags and a reserved field for future extensions. As 4108the kernel never checked for flags == 0 and QEMU never pre-zeroed flags and 4109reserved, these fields can not be used in the future without breaking 4110compatibility. 4111 4112If -ENOBUFS is returned the buffer provided was too small and userspace 4113may retry with a bigger buffer. 4114 41154.95 KVM_S390_SET_IRQ_STATE 4116--------------------------- 4117 4118:Capability: KVM_CAP_S390_IRQ_STATE 4119:Architectures: s390 4120:Type: vcpu ioctl 4121:Parameters: struct kvm_s390_irq_state (in) 4122:Returns: 0 on success, 4123 -EFAULT if the buffer address was invalid, 4124 -EINVAL for an invalid buffer length (see below), 4125 -EBUSY if there were already interrupts pending, 4126 errors occurring when actually injecting the 4127 interrupt. See KVM_S390_IRQ. 4128 4129This ioctl allows userspace to set the complete state of all cpu-local 4130interrupts currently pending for the vcpu. It is intended for restoring 4131interrupt state after a migration. The input parameter is a userspace buffer 4132containing a struct kvm_s390_irq_state:: 4133 4134 struct kvm_s390_irq_state { 4135 __u64 buf; 4136 __u32 flags; /* will stay unused for compatibility reasons */ 4137 __u32 len; 4138 __u32 reserved[4]; /* will stay unused for compatibility reasons */ 4139 }; 4140 4141The restrictions for flags and reserved apply as well. 4142(see KVM_S390_GET_IRQ_STATE) 4143 4144The userspace memory referenced by buf contains a struct kvm_s390_irq 4145for each interrupt to be injected into the guest. 4146If one of the interrupts could not be injected for some reason the 4147ioctl aborts. 4148 4149len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0 4150and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq), 4151which is the maximum number of possibly pending cpu-local interrupts. 4152 41534.96 KVM_SMI 4154------------ 4155 4156:Capability: KVM_CAP_X86_SMM 4157:Architectures: x86 4158:Type: vcpu ioctl 4159:Parameters: none 4160:Returns: 0 on success, -1 on error 4161 4162Queues an SMI on the thread's vcpu. 4163 41644.97 KVM_X86_SET_MSR_FILTER 4165---------------------------- 4166 4167:Capability: KVM_CAP_X86_MSR_FILTER 4168:Architectures: x86 4169:Type: vm ioctl 4170:Parameters: struct kvm_msr_filter 4171:Returns: 0 on success, < 0 on error 4172 4173:: 4174 4175 struct kvm_msr_filter_range { 4176 #define KVM_MSR_FILTER_READ (1 << 0) 4177 #define KVM_MSR_FILTER_WRITE (1 << 1) 4178 __u32 flags; 4179 __u32 nmsrs; /* number of msrs in bitmap */ 4180 __u32 base; /* MSR index the bitmap starts at */ 4181 __u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */ 4182 }; 4183 4184 #define KVM_MSR_FILTER_MAX_RANGES 16 4185 struct kvm_msr_filter { 4186 #define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0) 4187 #define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0) 4188 __u32 flags; 4189 struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES]; 4190 }; 4191 4192flags values for ``struct kvm_msr_filter_range``: 4193 4194``KVM_MSR_FILTER_READ`` 4195 4196 Filter read accesses to MSRs using the given bitmap. A 0 in the bitmap 4197 indicates that read accesses should be denied, while a 1 indicates that 4198 a read for a particular MSR should be allowed regardless of the default 4199 filter action. 4200 4201``KVM_MSR_FILTER_WRITE`` 4202 4203 Filter write accesses to MSRs using the given bitmap. A 0 in the bitmap 4204 indicates that write accesses should be denied, while a 1 indicates that 4205 a write for a particular MSR should be allowed regardless of the default 4206 filter action. 4207 4208flags values for ``struct kvm_msr_filter``: 4209 4210``KVM_MSR_FILTER_DEFAULT_ALLOW`` 4211 4212 If no filter range matches an MSR index that is getting accessed, KVM will 4213 allow accesses to all MSRs by default. 4214 4215``KVM_MSR_FILTER_DEFAULT_DENY`` 4216 4217 If no filter range matches an MSR index that is getting accessed, KVM will 4218 deny accesses to all MSRs by default. 4219 4220This ioctl allows userspace to define up to 16 bitmaps of MSR ranges to deny 4221guest MSR accesses that would normally be allowed by KVM. If an MSR is not 4222covered by a specific range, the "default" filtering behavior applies. Each 4223bitmap range covers MSRs from [base .. base+nmsrs). 4224 4225If an MSR access is denied by userspace, the resulting KVM behavior depends on 4226whether or not KVM_CAP_X86_USER_SPACE_MSR's KVM_MSR_EXIT_REASON_FILTER is 4227enabled. If KVM_MSR_EXIT_REASON_FILTER is enabled, KVM will exit to userspace 4228on denied accesses, i.e. userspace effectively intercepts the MSR access. If 4229KVM_MSR_EXIT_REASON_FILTER is not enabled, KVM will inject a #GP into the guest 4230on denied accesses. Note, if an MSR access is denied during emulation of MSR 4231load/stores during VMX transitions, KVM ignores KVM_MSR_EXIT_REASON_FILTER. 4232See the below warning for full details. 4233 4234If an MSR access is allowed by userspace, KVM will emulate and/or virtualize 4235the access in accordance with the vCPU model. Note, KVM may still ultimately 4236inject a #GP if an access is allowed by userspace, e.g. if KVM doesn't support 4237the MSR, or to follow architectural behavior for the MSR. 4238 4239By default, KVM operates in KVM_MSR_FILTER_DEFAULT_ALLOW mode with no MSR range 4240filters. 4241 4242Calling this ioctl with an empty set of ranges (all nmsrs == 0) disables MSR 4243filtering. In that mode, ``KVM_MSR_FILTER_DEFAULT_DENY`` is invalid and causes 4244an error. 4245 4246.. warning:: 4247 MSR accesses that are side effects of instruction execution (emulated or 4248 native) are not filtered as hardware does not honor MSR bitmaps outside of 4249 RDMSR and WRMSR, and KVM mimics that behavior when emulating instructions 4250 to avoid pointless divergence from hardware. E.g. RDPID reads MSR_TSC_AUX, 4251 SYSENTER reads the SYSENTER MSRs, etc. 4252 4253 MSRs that are loaded/stored via dedicated VMCS fields are not filtered as 4254 part of VM-Enter/VM-Exit emulation. 4255 4256 MSRs that are loaded/store via VMX's load/store lists _are_ filtered as part 4257 of VM-Enter/VM-Exit emulation. If an MSR access is denied on VM-Enter, KVM 4258 synthesizes a consistency check VM-Exit(EXIT_REASON_MSR_LOAD_FAIL). If an 4259 MSR access is denied on VM-Exit, KVM synthesizes a VM-Abort. In short, KVM 4260 extends Intel's architectural list of MSRs that cannot be loaded/saved via 4261 the VM-Enter/VM-Exit MSR list. It is platform owner's responsibility to 4262 to communicate any such restrictions to their end users. 4263 4264 x2APIC MSR accesses cannot be filtered (KVM silently ignores filters that 4265 cover any x2APIC MSRs). 4266 4267Note, invoking this ioctl while a vCPU is running is inherently racy. However, 4268KVM does guarantee that vCPUs will see either the previous filter or the new 4269filter, e.g. MSRs with identical settings in both the old and new filter will 4270have deterministic behavior. 4271 4272Similarly, if userspace wishes to intercept on denied accesses, 4273KVM_MSR_EXIT_REASON_FILTER must be enabled before activating any filters, and 4274left enabled until after all filters are deactivated. Failure to do so may 4275result in KVM injecting a #GP instead of exiting to userspace. 4276 42774.98 KVM_CREATE_SPAPR_TCE_64 4278---------------------------- 4279 4280:Capability: KVM_CAP_SPAPR_TCE_64 4281:Architectures: powerpc 4282:Type: vm ioctl 4283:Parameters: struct kvm_create_spapr_tce_64 (in) 4284:Returns: file descriptor for manipulating the created TCE table 4285 4286This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit 4287windows, described in 4.62 KVM_CREATE_SPAPR_TCE 4288 4289This capability uses extended struct in ioctl interface:: 4290 4291 /* for KVM_CAP_SPAPR_TCE_64 */ 4292 struct kvm_create_spapr_tce_64 { 4293 __u64 liobn; 4294 __u32 page_shift; 4295 __u32 flags; 4296 __u64 offset; /* in pages */ 4297 __u64 size; /* in pages */ 4298 }; 4299 4300The aim of extension is to support an additional bigger DMA window with 4301a variable page size. 4302KVM_CREATE_SPAPR_TCE_64 receives a 64bit window size, an IOMMU page shift and 4303a bus offset of the corresponding DMA window, @size and @offset are numbers 4304of IOMMU pages. 4305 4306@flags are not used at the moment. 4307 4308The rest of functionality is identical to KVM_CREATE_SPAPR_TCE. 4309 43104.99 KVM_REINJECT_CONTROL 4311------------------------- 4312 4313:Capability: KVM_CAP_REINJECT_CONTROL 4314:Architectures: x86 4315:Type: vm ioctl 4316:Parameters: struct kvm_reinject_control (in) 4317:Returns: 0 on success, 4318 -EFAULT if struct kvm_reinject_control cannot be read, 4319 -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier. 4320 4321i8254 (PIT) has two modes, reinject and !reinject. The default is reinject, 4322where KVM queues elapsed i8254 ticks and monitors completion of interrupt from 4323vector(s) that i8254 injects. Reinject mode dequeues a tick and injects its 4324interrupt whenever there isn't a pending interrupt from i8254. 4325!reinject mode injects an interrupt as soon as a tick arrives. 4326 4327:: 4328 4329 struct kvm_reinject_control { 4330 __u8 pit_reinject; 4331 __u8 reserved[31]; 4332 }; 4333 4334pit_reinject = 0 (!reinject mode) is recommended, unless running an old 4335operating system that uses the PIT for timing (e.g. Linux 2.4.x). 4336 43374.100 KVM_PPC_CONFIGURE_V3_MMU 4338------------------------------ 4339 4340:Capability: KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 4341:Architectures: ppc 4342:Type: vm ioctl 4343:Parameters: struct kvm_ppc_mmuv3_cfg (in) 4344:Returns: 0 on success, 4345 -EFAULT if struct kvm_ppc_mmuv3_cfg cannot be read, 4346 -EINVAL if the configuration is invalid 4347 4348This ioctl controls whether the guest will use radix or HPT (hashed 4349page table) translation, and sets the pointer to the process table for 4350the guest. 4351 4352:: 4353 4354 struct kvm_ppc_mmuv3_cfg { 4355 __u64 flags; 4356 __u64 process_table; 4357 }; 4358 4359There are two bits that can be set in flags; KVM_PPC_MMUV3_RADIX and 4360KVM_PPC_MMUV3_GTSE. KVM_PPC_MMUV3_RADIX, if set, configures the guest 4361to use radix tree translation, and if clear, to use HPT translation. 4362KVM_PPC_MMUV3_GTSE, if set and if KVM permits it, configures the guest 4363to be able to use the global TLB and SLB invalidation instructions; 4364if clear, the guest may not use these instructions. 4365 4366The process_table field specifies the address and size of the guest 4367process table, which is in the guest's space. This field is formatted 4368as the second doubleword of the partition table entry, as defined in 4369the Power ISA V3.00, Book III section 5.7.6.1. 4370 43714.101 KVM_PPC_GET_RMMU_INFO 4372--------------------------- 4373 4374:Capability: KVM_CAP_PPC_MMU_RADIX 4375:Architectures: ppc 4376:Type: vm ioctl 4377:Parameters: struct kvm_ppc_rmmu_info (out) 4378:Returns: 0 on success, 4379 -EFAULT if struct kvm_ppc_rmmu_info cannot be written, 4380 -EINVAL if no useful information can be returned 4381 4382This ioctl returns a structure containing two things: (a) a list 4383containing supported radix tree geometries, and (b) a list that maps 4384page sizes to put in the "AP" (actual page size) field for the tlbie 4385(TLB invalidate entry) instruction. 4386 4387:: 4388 4389 struct kvm_ppc_rmmu_info { 4390 struct kvm_ppc_radix_geom { 4391 __u8 page_shift; 4392 __u8 level_bits[4]; 4393 __u8 pad[3]; 4394 } geometries[8]; 4395 __u32 ap_encodings[8]; 4396 }; 4397 4398The geometries[] field gives up to 8 supported geometries for the 4399radix page table, in terms of the log base 2 of the smallest page 4400size, and the number of bits indexed at each level of the tree, from 4401the PTE level up to the PGD level in that order. Any unused entries 4402will have 0 in the page_shift field. 4403 4404The ap_encodings gives the supported page sizes and their AP field 4405encodings, encoded with the AP value in the top 3 bits and the log 4406base 2 of the page size in the bottom 6 bits. 4407 44084.102 KVM_PPC_RESIZE_HPT_PREPARE 4409-------------------------------- 4410 4411:Capability: KVM_CAP_SPAPR_RESIZE_HPT 4412:Architectures: powerpc 4413:Type: vm ioctl 4414:Parameters: struct kvm_ppc_resize_hpt (in) 4415:Returns: 0 on successful completion, 4416 >0 if a new HPT is being prepared, the value is an estimated 4417 number of milliseconds until preparation is complete, 4418 -EFAULT if struct kvm_reinject_control cannot be read, 4419 -EINVAL if the supplied shift or flags are invalid, 4420 -ENOMEM if unable to allocate the new HPT, 4421 4422Used to implement the PAPR extension for runtime resizing of a guest's 4423Hashed Page Table (HPT). Specifically this starts, stops or monitors 4424the preparation of a new potential HPT for the guest, essentially 4425implementing the H_RESIZE_HPT_PREPARE hypercall. 4426 4427:: 4428 4429 struct kvm_ppc_resize_hpt { 4430 __u64 flags; 4431 __u32 shift; 4432 __u32 pad; 4433 }; 4434 4435If called with shift > 0 when there is no pending HPT for the guest, 4436this begins preparation of a new pending HPT of size 2^(shift) bytes. 4437It then returns a positive integer with the estimated number of 4438milliseconds until preparation is complete. 4439 4440If called when there is a pending HPT whose size does not match that 4441requested in the parameters, discards the existing pending HPT and 4442creates a new one as above. 4443 4444If called when there is a pending HPT of the size requested, will: 4445 4446 * If preparation of the pending HPT is already complete, return 0 4447 * If preparation of the pending HPT has failed, return an error 4448 code, then discard the pending HPT. 4449 * If preparation of the pending HPT is still in progress, return an 4450 estimated number of milliseconds until preparation is complete. 4451 4452If called with shift == 0, discards any currently pending HPT and 4453returns 0 (i.e. cancels any in-progress preparation). 4454 4455flags is reserved for future expansion, currently setting any bits in 4456flags will result in an -EINVAL. 4457 4458Normally this will be called repeatedly with the same parameters until 4459it returns <= 0. The first call will initiate preparation, subsequent 4460ones will monitor preparation until it completes or fails. 4461 44624.103 KVM_PPC_RESIZE_HPT_COMMIT 4463------------------------------- 4464 4465:Capability: KVM_CAP_SPAPR_RESIZE_HPT 4466:Architectures: powerpc 4467:Type: vm ioctl 4468:Parameters: struct kvm_ppc_resize_hpt (in) 4469:Returns: 0 on successful completion, 4470 -EFAULT if struct kvm_reinject_control cannot be read, 4471 -EINVAL if the supplied shift or flags are invalid, 4472 -ENXIO is there is no pending HPT, or the pending HPT doesn't 4473 have the requested size, 4474 -EBUSY if the pending HPT is not fully prepared, 4475 -ENOSPC if there was a hash collision when moving existing 4476 HPT entries to the new HPT, 4477 -EIO on other error conditions 4478 4479Used to implement the PAPR extension for runtime resizing of a guest's 4480Hashed Page Table (HPT). Specifically this requests that the guest be 4481transferred to working with the new HPT, essentially implementing the 4482H_RESIZE_HPT_COMMIT hypercall. 4483 4484:: 4485 4486 struct kvm_ppc_resize_hpt { 4487 __u64 flags; 4488 __u32 shift; 4489 __u32 pad; 4490 }; 4491 4492This should only be called after KVM_PPC_RESIZE_HPT_PREPARE has 4493returned 0 with the same parameters. In other cases 4494KVM_PPC_RESIZE_HPT_COMMIT will return an error (usually -ENXIO or 4495-EBUSY, though others may be possible if the preparation was started, 4496but failed). 4497 4498This will have undefined effects on the guest if it has not already 4499placed itself in a quiescent state where no vcpu will make MMU enabled 4500memory accesses. 4501 4502On successful completion, the pending HPT will become the guest's active 4503HPT and the previous HPT will be discarded. 4504 4505On failure, the guest will still be operating on its previous HPT. 4506 45074.104 KVM_X86_GET_MCE_CAP_SUPPORTED 4508----------------------------------- 4509 4510:Capability: KVM_CAP_MCE 4511:Architectures: x86 4512:Type: system ioctl 4513:Parameters: u64 mce_cap (out) 4514:Returns: 0 on success, -1 on error 4515 4516Returns supported MCE capabilities. The u64 mce_cap parameter 4517has the same format as the MSR_IA32_MCG_CAP register. Supported 4518capabilities will have the corresponding bits set. 4519 45204.105 KVM_X86_SETUP_MCE 4521----------------------- 4522 4523:Capability: KVM_CAP_MCE 4524:Architectures: x86 4525:Type: vcpu ioctl 4526:Parameters: u64 mcg_cap (in) 4527:Returns: 0 on success, 4528 -EFAULT if u64 mcg_cap cannot be read, 4529 -EINVAL if the requested number of banks is invalid, 4530 -EINVAL if requested MCE capability is not supported. 4531 4532Initializes MCE support for use. The u64 mcg_cap parameter 4533has the same format as the MSR_IA32_MCG_CAP register and 4534specifies which capabilities should be enabled. The maximum 4535supported number of error-reporting banks can be retrieved when 4536checking for KVM_CAP_MCE. The supported capabilities can be 4537retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED. 4538 45394.106 KVM_X86_SET_MCE 4540--------------------- 4541 4542:Capability: KVM_CAP_MCE 4543:Architectures: x86 4544:Type: vcpu ioctl 4545:Parameters: struct kvm_x86_mce (in) 4546:Returns: 0 on success, 4547 -EFAULT if struct kvm_x86_mce cannot be read, 4548 -EINVAL if the bank number is invalid, 4549 -EINVAL if VAL bit is not set in status field. 4550 4551Inject a machine check error (MCE) into the guest. The input 4552parameter is:: 4553 4554 struct kvm_x86_mce { 4555 __u64 status; 4556 __u64 addr; 4557 __u64 misc; 4558 __u64 mcg_status; 4559 __u8 bank; 4560 __u8 pad1[7]; 4561 __u64 pad2[3]; 4562 }; 4563 4564If the MCE being reported is an uncorrected error, KVM will 4565inject it as an MCE exception into the guest. If the guest 4566MCG_STATUS register reports that an MCE is in progress, KVM 4567causes an KVM_EXIT_SHUTDOWN vmexit. 4568 4569Otherwise, if the MCE is a corrected error, KVM will just 4570store it in the corresponding bank (provided this bank is 4571not holding a previously reported uncorrected error). 4572 45734.107 KVM_S390_GET_CMMA_BITS 4574---------------------------- 4575 4576:Capability: KVM_CAP_S390_CMMA_MIGRATION 4577:Architectures: s390 4578:Type: vm ioctl 4579:Parameters: struct kvm_s390_cmma_log (in, out) 4580:Returns: 0 on success, a negative value on error 4581 4582Errors: 4583 4584 ====== ============================================================= 4585 ENOMEM not enough memory can be allocated to complete the task 4586 ENXIO if CMMA is not enabled 4587 EINVAL if KVM_S390_CMMA_PEEK is not set but migration mode was not enabled 4588 EINVAL if KVM_S390_CMMA_PEEK is not set but dirty tracking has been 4589 disabled (and thus migration mode was automatically disabled) 4590 EFAULT if the userspace address is invalid or if no page table is 4591 present for the addresses (e.g. when using hugepages). 4592 ====== ============================================================= 4593 4594This ioctl is used to get the values of the CMMA bits on the s390 4595architecture. It is meant to be used in two scenarios: 4596 4597- During live migration to save the CMMA values. Live migration needs 4598 to be enabled via the KVM_REQ_START_MIGRATION VM property. 4599- To non-destructively peek at the CMMA values, with the flag 4600 KVM_S390_CMMA_PEEK set. 4601 4602The ioctl takes parameters via the kvm_s390_cmma_log struct. The desired 4603values are written to a buffer whose location is indicated via the "values" 4604member in the kvm_s390_cmma_log struct. The values in the input struct are 4605also updated as needed. 4606 4607Each CMMA value takes up one byte. 4608 4609:: 4610 4611 struct kvm_s390_cmma_log { 4612 __u64 start_gfn; 4613 __u32 count; 4614 __u32 flags; 4615 union { 4616 __u64 remaining; 4617 __u64 mask; 4618 }; 4619 __u64 values; 4620 }; 4621 4622start_gfn is the number of the first guest frame whose CMMA values are 4623to be retrieved, 4624 4625count is the length of the buffer in bytes, 4626 4627values points to the buffer where the result will be written to. 4628 4629If count is greater than KVM_S390_SKEYS_MAX, then it is considered to be 4630KVM_S390_SKEYS_MAX. KVM_S390_SKEYS_MAX is re-used for consistency with 4631other ioctls. 4632 4633The result is written in the buffer pointed to by the field values, and 4634the values of the input parameter are updated as follows. 4635 4636Depending on the flags, different actions are performed. The only 4637supported flag so far is KVM_S390_CMMA_PEEK. 4638 4639The default behaviour if KVM_S390_CMMA_PEEK is not set is: 4640start_gfn will indicate the first page frame whose CMMA bits were dirty. 4641It is not necessarily the same as the one passed as input, as clean pages 4642are skipped. 4643 4644count will indicate the number of bytes actually written in the buffer. 4645It can (and very often will) be smaller than the input value, since the 4646buffer is only filled until 16 bytes of clean values are found (which 4647are then not copied in the buffer). Since a CMMA migration block needs 4648the base address and the length, for a total of 16 bytes, we will send 4649back some clean data if there is some dirty data afterwards, as long as 4650the size of the clean data does not exceed the size of the header. This 4651allows to minimize the amount of data to be saved or transferred over 4652the network at the expense of more roundtrips to userspace. The next 4653invocation of the ioctl will skip over all the clean values, saving 4654potentially more than just the 16 bytes we found. 4655 4656If KVM_S390_CMMA_PEEK is set: 4657the existing storage attributes are read even when not in migration 4658mode, and no other action is performed; 4659 4660the output start_gfn will be equal to the input start_gfn, 4661 4662the output count will be equal to the input count, except if the end of 4663memory has been reached. 4664 4665In both cases: 4666the field "remaining" will indicate the total number of dirty CMMA values 4667still remaining, or 0 if KVM_S390_CMMA_PEEK is set and migration mode is 4668not enabled. 4669 4670mask is unused. 4671 4672values points to the userspace buffer where the result will be stored. 4673 46744.108 KVM_S390_SET_CMMA_BITS 4675---------------------------- 4676 4677:Capability: KVM_CAP_S390_CMMA_MIGRATION 4678:Architectures: s390 4679:Type: vm ioctl 4680:Parameters: struct kvm_s390_cmma_log (in) 4681:Returns: 0 on success, a negative value on error 4682 4683This ioctl is used to set the values of the CMMA bits on the s390 4684architecture. It is meant to be used during live migration to restore 4685the CMMA values, but there are no restrictions on its use. 4686The ioctl takes parameters via the kvm_s390_cmma_values struct. 4687Each CMMA value takes up one byte. 4688 4689:: 4690 4691 struct kvm_s390_cmma_log { 4692 __u64 start_gfn; 4693 __u32 count; 4694 __u32 flags; 4695 union { 4696 __u64 remaining; 4697 __u64 mask; 4698 }; 4699 __u64 values; 4700 }; 4701 4702start_gfn indicates the starting guest frame number, 4703 4704count indicates how many values are to be considered in the buffer, 4705 4706flags is not used and must be 0. 4707 4708mask indicates which PGSTE bits are to be considered. 4709 4710remaining is not used. 4711 4712values points to the buffer in userspace where to store the values. 4713 4714This ioctl can fail with -ENOMEM if not enough memory can be allocated to 4715complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if 4716the count field is too large (e.g. more than KVM_S390_CMMA_SIZE_MAX) or 4717if the flags field was not 0, with -EFAULT if the userspace address is 4718invalid, if invalid pages are written to (e.g. after the end of memory) 4719or if no page table is present for the addresses (e.g. when using 4720hugepages). 4721 47224.109 KVM_PPC_GET_CPU_CHAR 4723-------------------------- 4724 4725:Capability: KVM_CAP_PPC_GET_CPU_CHAR 4726:Architectures: powerpc 4727:Type: vm ioctl 4728:Parameters: struct kvm_ppc_cpu_char (out) 4729:Returns: 0 on successful completion, 4730 -EFAULT if struct kvm_ppc_cpu_char cannot be written 4731 4732This ioctl gives userspace information about certain characteristics 4733of the CPU relating to speculative execution of instructions and 4734possible information leakage resulting from speculative execution (see 4735CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754). The information is 4736returned in struct kvm_ppc_cpu_char, which looks like this:: 4737 4738 struct kvm_ppc_cpu_char { 4739 __u64 character; /* characteristics of the CPU */ 4740 __u64 behaviour; /* recommended software behaviour */ 4741 __u64 character_mask; /* valid bits in character */ 4742 __u64 behaviour_mask; /* valid bits in behaviour */ 4743 }; 4744 4745For extensibility, the character_mask and behaviour_mask fields 4746indicate which bits of character and behaviour have been filled in by 4747the kernel. If the set of defined bits is extended in future then 4748userspace will be able to tell whether it is running on a kernel that 4749knows about the new bits. 4750 4751The character field describes attributes of the CPU which can help 4752with preventing inadvertent information disclosure - specifically, 4753whether there is an instruction to flash-invalidate the L1 data cache 4754(ori 30,30,0 or mtspr SPRN_TRIG2,rN), whether the L1 data cache is set 4755to a mode where entries can only be used by the thread that created 4756them, whether the bcctr[l] instruction prevents speculation, and 4757whether a speculation barrier instruction (ori 31,31,0) is provided. 4758 4759The behaviour field describes actions that software should take to 4760prevent inadvertent information disclosure, and thus describes which 4761vulnerabilities the hardware is subject to; specifically whether the 4762L1 data cache should be flushed when returning to user mode from the 4763kernel, and whether a speculation barrier should be placed between an 4764array bounds check and the array access. 4765 4766These fields use the same bit definitions as the new 4767H_GET_CPU_CHARACTERISTICS hypercall. 4768 47694.110 KVM_MEMORY_ENCRYPT_OP 4770--------------------------- 4771 4772:Capability: basic 4773:Architectures: x86 4774:Type: vm ioctl, vcpu ioctl 4775:Parameters: an opaque platform specific structure (in/out) 4776:Returns: 0 on success; -1 on error 4777 4778If the platform supports creating encrypted VMs then this ioctl can be used 4779for issuing platform-specific memory encryption commands to manage those 4780encrypted VMs. 4781 4782Currently, this ioctl is used for issuing both Secure Encrypted Virtualization 4783(SEV) commands on AMD Processors and Trusted Domain Extensions (TDX) commands 4784on Intel Processors. The detailed commands are defined in 4785Documentation/virt/kvm/x86/amd-memory-encryption.rst and 4786Documentation/virt/kvm/x86/intel-tdx.rst. 4787 47884.111 KVM_MEMORY_ENCRYPT_REG_REGION 4789----------------------------------- 4790 4791:Capability: basic 4792:Architectures: x86 4793:Type: system 4794:Parameters: struct kvm_enc_region (in) 4795:Returns: 0 on success; -1 on error 4796 4797This ioctl can be used to register a guest memory region which may 4798contain encrypted data (e.g. guest RAM, SMRAM etc). 4799 4800It is used in the SEV-enabled guest. When encryption is enabled, a guest 4801memory region may contain encrypted data. The SEV memory encryption 4802engine uses a tweak such that two identical plaintext pages, each at 4803different locations will have differing ciphertexts. So swapping or 4804moving ciphertext of those pages will not result in plaintext being 4805swapped. So relocating (or migrating) physical backing pages for the SEV 4806guest will require some additional steps. 4807 4808Note: The current SEV key management spec does not provide commands to 4809swap or migrate (move) ciphertext pages. Hence, for now we pin the guest 4810memory region registered with the ioctl. 4811 48124.112 KVM_MEMORY_ENCRYPT_UNREG_REGION 4813------------------------------------- 4814 4815:Capability: basic 4816:Architectures: x86 4817:Type: system 4818:Parameters: struct kvm_enc_region (in) 4819:Returns: 0 on success; -1 on error 4820 4821This ioctl can be used to unregister the guest memory region registered 4822with KVM_MEMORY_ENCRYPT_REG_REGION ioctl above. 4823 48244.113 KVM_HYPERV_EVENTFD 4825------------------------ 4826 4827:Capability: KVM_CAP_HYPERV_EVENTFD 4828:Architectures: x86 4829:Type: vm ioctl 4830:Parameters: struct kvm_hyperv_eventfd (in) 4831 4832This ioctl (un)registers an eventfd to receive notifications from the guest on 4833the specified Hyper-V connection id through the SIGNAL_EVENT hypercall, without 4834causing a user exit. SIGNAL_EVENT hypercall with non-zero event flag number 4835(bits 24-31) still triggers a KVM_EXIT_HYPERV_HCALL user exit. 4836 4837:: 4838 4839 struct kvm_hyperv_eventfd { 4840 __u32 conn_id; 4841 __s32 fd; 4842 __u32 flags; 4843 __u32 padding[3]; 4844 }; 4845 4846The conn_id field should fit within 24 bits:: 4847 4848 #define KVM_HYPERV_CONN_ID_MASK 0x00ffffff 4849 4850The acceptable values for the flags field are:: 4851 4852 #define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) 4853 4854:Returns: 0 on success, 4855 -EINVAL if conn_id or flags is outside the allowed range, 4856 -ENOENT on deassign if the conn_id isn't registered, 4857 -EEXIST on assign if the conn_id is already registered 4858 48594.114 KVM_GET_NESTED_STATE 4860-------------------------- 4861 4862:Capability: KVM_CAP_NESTED_STATE 4863:Architectures: x86 4864:Type: vcpu ioctl 4865:Parameters: struct kvm_nested_state (in/out) 4866:Returns: 0 on success, -1 on error 4867 4868Errors: 4869 4870 ===== ============================================================= 4871 E2BIG the total state size exceeds the value of 'size' specified by 4872 the user; the size required will be written into size. 4873 ===== ============================================================= 4874 4875:: 4876 4877 struct kvm_nested_state { 4878 __u16 flags; 4879 __u16 format; 4880 __u32 size; 4881 4882 union { 4883 struct kvm_vmx_nested_state_hdr vmx; 4884 struct kvm_svm_nested_state_hdr svm; 4885 4886 /* Pad the header to 128 bytes. */ 4887 __u8 pad[120]; 4888 } hdr; 4889 4890 union { 4891 struct kvm_vmx_nested_state_data vmx[0]; 4892 struct kvm_svm_nested_state_data svm[0]; 4893 } data; 4894 }; 4895 4896 #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 4897 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 4898 #define KVM_STATE_NESTED_EVMCS 0x00000004 4899 4900 #define KVM_STATE_NESTED_FORMAT_VMX 0 4901 #define KVM_STATE_NESTED_FORMAT_SVM 1 4902 4903 #define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000 4904 4905 #define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE 0x00000001 4906 #define KVM_STATE_NESTED_VMX_SMM_VMXON 0x00000002 4907 4908 #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 4909 4910 struct kvm_vmx_nested_state_hdr { 4911 __u64 vmxon_pa; 4912 __u64 vmcs12_pa; 4913 4914 struct { 4915 __u16 flags; 4916 } smm; 4917 4918 __u32 flags; 4919 __u64 preemption_timer_deadline; 4920 }; 4921 4922 struct kvm_vmx_nested_state_data { 4923 __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; 4924 __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; 4925 }; 4926 4927This ioctl copies the vcpu's nested virtualization state from the kernel to 4928userspace. 4929 4930The maximum size of the state can be retrieved by passing KVM_CAP_NESTED_STATE 4931to the KVM_CHECK_EXTENSION ioctl(). 4932 49334.115 KVM_SET_NESTED_STATE 4934-------------------------- 4935 4936:Capability: KVM_CAP_NESTED_STATE 4937:Architectures: x86 4938:Type: vcpu ioctl 4939:Parameters: struct kvm_nested_state (in) 4940:Returns: 0 on success, -1 on error 4941 4942This copies the vcpu's kvm_nested_state struct from userspace to the kernel. 4943For the definition of struct kvm_nested_state, see KVM_GET_NESTED_STATE. 4944 49454.116 KVM_(UN)REGISTER_COALESCED_MMIO 4946------------------------------------- 4947 4948:Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio) 4949 KVM_CAP_COALESCED_PIO (for coalesced pio) 4950:Architectures: all 4951:Type: vm ioctl 4952:Parameters: struct kvm_coalesced_mmio_zone 4953:Returns: 0 on success, < 0 on error 4954 4955Coalesced I/O is a performance optimization that defers hardware 4956register write emulation so that userspace exits are avoided. It is 4957typically used to reduce the overhead of emulating frequently accessed 4958hardware registers. 4959 4960When a hardware register is configured for coalesced I/O, write accesses 4961do not exit to userspace and their value is recorded in a ring buffer 4962that is shared between kernel and userspace. 4963 4964Coalesced I/O is used if one or more write accesses to a hardware 4965register can be deferred until a read or a write to another hardware 4966register on the same device. This last access will cause a vmexit and 4967userspace will process accesses from the ring buffer before emulating 4968it. That will avoid exiting to userspace on repeated writes. 4969 4970Coalesced pio is based on coalesced mmio. There is little difference 4971between coalesced mmio and pio except that coalesced pio records accesses 4972to I/O ports. 4973 49744.117 KVM_CLEAR_DIRTY_LOG 4975------------------------- 4976 4977:Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 4978:Architectures: x86, arm64, mips 4979:Type: vm ioctl 4980:Parameters: struct kvm_clear_dirty_log (in) 4981:Returns: 0 on success, -1 on error 4982 4983:: 4984 4985 /* for KVM_CLEAR_DIRTY_LOG */ 4986 struct kvm_clear_dirty_log { 4987 __u32 slot; 4988 __u32 num_pages; 4989 __u64 first_page; 4990 union { 4991 void __user *dirty_bitmap; /* one bit per page */ 4992 __u64 padding; 4993 }; 4994 }; 4995 4996The ioctl clears the dirty status of pages in a memory slot, according to 4997the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap 4998field. Bit 0 of the bitmap corresponds to page "first_page" in the 4999memory slot, and num_pages is the size in bits of the input bitmap. 5000first_page must be a multiple of 64; num_pages must also be a multiple of 500164 unless first_page + num_pages is the size of the memory slot. For each 5002bit that is set in the input bitmap, the corresponding page is marked "clean" 5003in KVM's dirty bitmap, and dirty tracking is re-enabled for that page 5004(for example via write-protection, or by clearing the dirty bit in 5005a page table entry). 5006 5007If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of slot field specifies 5008the address space for which you want to clear the dirty status. See 5009KVM_SET_USER_MEMORY_REGION for details on the usage of slot field. 5010 5011This ioctl is mostly useful when KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 5012is enabled; for more information, see the description of the capability. 5013However, it can always be used as long as KVM_CHECK_EXTENSION confirms 5014that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is present. 5015 50164.118 KVM_GET_SUPPORTED_HV_CPUID 5017-------------------------------- 5018 5019:Capability: KVM_CAP_HYPERV_CPUID (vcpu), KVM_CAP_SYS_HYPERV_CPUID (system) 5020:Architectures: x86 5021:Type: system ioctl, vcpu ioctl 5022:Parameters: struct kvm_cpuid2 (in/out) 5023:Returns: 0 on success, -1 on error 5024 5025:: 5026 5027 struct kvm_cpuid2 { 5028 __u32 nent; 5029 __u32 padding; 5030 struct kvm_cpuid_entry2 entries[0]; 5031 }; 5032 5033 struct kvm_cpuid_entry2 { 5034 __u32 function; 5035 __u32 index; 5036 __u32 flags; 5037 __u32 eax; 5038 __u32 ebx; 5039 __u32 ecx; 5040 __u32 edx; 5041 __u32 padding[3]; 5042 }; 5043 5044This ioctl returns x86 cpuid features leaves related to Hyper-V emulation in 5045KVM. Userspace can use the information returned by this ioctl to construct 5046cpuid information presented to guests consuming Hyper-V enlightenments (e.g. 5047Windows or Hyper-V guests). 5048 5049CPUID feature leaves returned by this ioctl are defined by Hyper-V Top Level 5050Functional Specification (TLFS). These leaves can't be obtained with 5051KVM_GET_SUPPORTED_CPUID ioctl because some of them intersect with KVM feature 5052leaves (0x40000000, 0x40000001). 5053 5054Currently, the following list of CPUID leaves are returned: 5055 5056 - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS 5057 - HYPERV_CPUID_INTERFACE 5058 - HYPERV_CPUID_VERSION 5059 - HYPERV_CPUID_FEATURES 5060 - HYPERV_CPUID_ENLIGHTMENT_INFO 5061 - HYPERV_CPUID_IMPLEMENT_LIMITS 5062 - HYPERV_CPUID_NESTED_FEATURES 5063 - HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS 5064 - HYPERV_CPUID_SYNDBG_INTERFACE 5065 - HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES 5066 5067Userspace invokes KVM_GET_SUPPORTED_HV_CPUID by passing a kvm_cpuid2 structure 5068with the 'nent' field indicating the number of entries in the variable-size 5069array 'entries'. If the number of entries is too low to describe all Hyper-V 5070feature leaves, an error (E2BIG) is returned. If the number is more or equal 5071to the number of Hyper-V feature leaves, the 'nent' field is adjusted to the 5072number of valid entries in the 'entries' array, which is then filled. 5073 5074'index' and 'flags' fields in 'struct kvm_cpuid_entry2' are currently reserved, 5075userspace should not expect to get any particular value there. 5076 5077Note, vcpu version of KVM_GET_SUPPORTED_HV_CPUID is currently deprecated. Unlike 5078system ioctl which exposes all supported feature bits unconditionally, vcpu 5079version has the following quirks: 5080 5081- HYPERV_CPUID_NESTED_FEATURES leaf and HV_X64_ENLIGHTENED_VMCS_RECOMMENDED 5082 feature bit are only exposed when Enlightened VMCS was previously enabled 5083 on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS). 5084- HV_STIMER_DIRECT_MODE_AVAILABLE bit is only exposed with in-kernel LAPIC. 5085 (presumes KVM_CREATE_IRQCHIP has already been called). 5086 50874.119 KVM_ARM_VCPU_FINALIZE 5088--------------------------- 5089 5090:Architectures: arm64 5091:Type: vcpu ioctl 5092:Parameters: int feature (in) 5093:Returns: 0 on success, -1 on error 5094 5095Errors: 5096 5097 ====== ============================================================== 5098 EPERM feature not enabled, needs configuration, or already finalized 5099 EINVAL feature unknown or not present 5100 ====== ============================================================== 5101 5102Recognised values for feature: 5103 5104 ===== =========================================== 5105 arm64 KVM_ARM_VCPU_SVE (requires KVM_CAP_ARM_SVE) 5106 ===== =========================================== 5107 5108Finalizes the configuration of the specified vcpu feature. 5109 5110The vcpu must already have been initialised, enabling the affected feature, by 5111means of a successful :ref:`KVM_ARM_VCPU_INIT <KVM_ARM_VCPU_INIT>` call with the 5112appropriate flag set in features[]. 5113 5114For affected vcpu features, this is a mandatory step that must be performed 5115before the vcpu is fully usable. 5116 5117Between KVM_ARM_VCPU_INIT and KVM_ARM_VCPU_FINALIZE, the feature may be 5118configured by use of ioctls such as KVM_SET_ONE_REG. The exact configuration 5119that should be performed and how to do it are feature-dependent. 5120 5121Other calls that depend on a particular feature being finalized, such as 5122KVM_RUN, KVM_GET_REG_LIST, KVM_GET_ONE_REG and KVM_SET_ONE_REG, will fail with 5123-EPERM unless the feature has already been finalized by means of a 5124KVM_ARM_VCPU_FINALIZE call. 5125 5126See KVM_ARM_VCPU_INIT for details of vcpu features that require finalization 5127using this ioctl. 5128 51294.120 KVM_SET_PMU_EVENT_FILTER 5130------------------------------ 5131 5132:Capability: KVM_CAP_PMU_EVENT_FILTER 5133:Architectures: x86 5134:Type: vm ioctl 5135:Parameters: struct kvm_pmu_event_filter (in) 5136:Returns: 0 on success, -1 on error 5137 5138Errors: 5139 5140 ====== ============================================================ 5141 EFAULT args[0] cannot be accessed 5142 EINVAL args[0] contains invalid data in the filter or filter events 5143 E2BIG nevents is too large 5144 EBUSY not enough memory to allocate the filter 5145 ====== ============================================================ 5146 5147:: 5148 5149 struct kvm_pmu_event_filter { 5150 __u32 action; 5151 __u32 nevents; 5152 __u32 fixed_counter_bitmap; 5153 __u32 flags; 5154 __u32 pad[4]; 5155 __u64 events[0]; 5156 }; 5157 5158This ioctl restricts the set of PMU events the guest can program by limiting 5159which event select and unit mask combinations are permitted. 5160 5161The argument holds a list of filter events which will be allowed or denied. 5162 5163Filter events only control general purpose counters; fixed purpose counters 5164are controlled by the fixed_counter_bitmap. 5165 5166Valid values for 'flags':: 5167 5168``0`` 5169 5170To use this mode, clear the 'flags' field. 5171 5172In this mode each event will contain an event select + unit mask. 5173 5174When the guest attempts to program the PMU the guest's event select + 5175unit mask is compared against the filter events to determine whether the 5176guest should have access. 5177 5178``KVM_PMU_EVENT_FLAG_MASKED_EVENTS`` 5179:Capability: KVM_CAP_PMU_EVENT_MASKED_EVENTS 5180 5181In this mode each filter event will contain an event select, mask, match, and 5182exclude value. To encode a masked event use:: 5183 5184 KVM_PMU_ENCODE_MASKED_ENTRY() 5185 5186An encoded event will follow this layout:: 5187 5188 Bits Description 5189 ---- ----------- 5190 7:0 event select (low bits) 5191 15:8 umask match 5192 31:16 unused 5193 35:32 event select (high bits) 5194 36:54 unused 5195 55 exclude bit 5196 63:56 umask mask 5197 5198When the guest attempts to program the PMU, these steps are followed in 5199determining if the guest should have access: 5200 5201 1. Match the event select from the guest against the filter events. 5202 2. If a match is found, match the guest's unit mask to the mask and match 5203 values of the included filter events. 5204 I.e. (unit mask & mask) == match && !exclude. 5205 3. If a match is found, match the guest's unit mask to the mask and match 5206 values of the excluded filter events. 5207 I.e. (unit mask & mask) == match && exclude. 5208 4. 5209 a. If an included match is found and an excluded match is not found, filter 5210 the event. 5211 b. For everything else, do not filter the event. 5212 5. 5213 a. If the event is filtered and it's an allow list, allow the guest to 5214 program the event. 5215 b. If the event is filtered and it's a deny list, do not allow the guest to 5216 program the event. 5217 5218When setting a new pmu event filter, -EINVAL will be returned if any of the 5219unused fields are set or if any of the high bits (35:32) in the event 5220select are set when called on Intel. 5221 5222Valid values for 'action':: 5223 5224 #define KVM_PMU_EVENT_ALLOW 0 5225 #define KVM_PMU_EVENT_DENY 1 5226 5227Via this API, KVM userspace can also control the behavior of the VM's fixed 5228counters (if any) by configuring the "action" and "fixed_counter_bitmap" fields. 5229 5230Specifically, KVM follows the following pseudo-code when determining whether to 5231allow the guest FixCtr[i] to count its pre-defined fixed event:: 5232 5233 FixCtr[i]_is_allowed = (action == ALLOW) && (bitmap & BIT(i)) || 5234 (action == DENY) && !(bitmap & BIT(i)); 5235 FixCtr[i]_is_denied = !FixCtr[i]_is_allowed; 5236 5237KVM always consumes fixed_counter_bitmap, it's userspace's responsibility to 5238ensure fixed_counter_bitmap is set correctly, e.g. if userspace wants to define 5239a filter that only affects general purpose counters. 5240 5241Note, the "events" field also applies to fixed counters' hardcoded event_select 5242and unit_mask values. "fixed_counter_bitmap" has higher priority than "events" 5243if there is a contradiction between the two. 5244 52454.121 KVM_PPC_SVM_OFF 5246--------------------- 5247 5248:Capability: basic 5249:Architectures: powerpc 5250:Type: vm ioctl 5251:Parameters: none 5252:Returns: 0 on successful completion, 5253 5254Errors: 5255 5256 ====== ================================================================ 5257 EINVAL if ultravisor failed to terminate the secure guest 5258 ENOMEM if hypervisor failed to allocate new radix page tables for guest 5259 ====== ================================================================ 5260 5261This ioctl is used to turn off the secure mode of the guest or transition 5262the guest from secure mode to normal mode. This is invoked when the guest 5263is reset. This has no effect if called for a normal guest. 5264 5265This ioctl issues an ultravisor call to terminate the secure guest, 5266unpins the VPA pages and releases all the device pages that are used to 5267track the secure pages by hypervisor. 5268 52694.122 KVM_S390_NORMAL_RESET 5270--------------------------- 5271 5272:Capability: KVM_CAP_S390_VCPU_RESETS 5273:Architectures: s390 5274:Type: vcpu ioctl 5275:Parameters: none 5276:Returns: 0 5277 5278This ioctl resets VCPU registers and control structures according to 5279the cpu reset definition in the POP (Principles Of Operation). 5280 52814.123 KVM_S390_INITIAL_RESET 5282---------------------------- 5283 5284:Capability: basic 5285:Architectures: s390 5286:Type: vcpu ioctl 5287:Parameters: none 5288:Returns: 0 5289 5290This ioctl resets VCPU registers and control structures according to 5291the initial cpu reset definition in the POP. However, the cpu is not 5292put into ESA mode. This reset is a superset of the normal reset. 5293 52944.124 KVM_S390_CLEAR_RESET 5295-------------------------- 5296 5297:Capability: KVM_CAP_S390_VCPU_RESETS 5298:Architectures: s390 5299:Type: vcpu ioctl 5300:Parameters: none 5301:Returns: 0 5302 5303This ioctl resets VCPU registers and control structures according to 5304the clear cpu reset definition in the POP. However, the cpu is not put 5305into ESA mode. This reset is a superset of the initial reset. 5306 5307 53084.125 KVM_S390_PV_COMMAND 5309------------------------- 5310 5311:Capability: KVM_CAP_S390_PROTECTED 5312:Architectures: s390 5313:Type: vm ioctl 5314:Parameters: struct kvm_pv_cmd 5315:Returns: 0 on success, < 0 on error 5316 5317:: 5318 5319 struct kvm_pv_cmd { 5320 __u32 cmd; /* Command to be executed */ 5321 __u16 rc; /* Ultravisor return code */ 5322 __u16 rrc; /* Ultravisor return reason code */ 5323 __u64 data; /* Data or address */ 5324 __u32 flags; /* flags for future extensions. Must be 0 for now */ 5325 __u32 reserved[3]; 5326 }; 5327 5328**Ultravisor return codes** 5329The Ultravisor return (reason) codes are provided by the kernel if a 5330Ultravisor call has been executed to achieve the results expected by 5331the command. Therefore they are independent of the IOCTL return 5332code. If KVM changes `rc`, its value will always be greater than 0 5333hence setting it to 0 before issuing a PV command is advised to be 5334able to detect a change of `rc`. 5335 5336**cmd values:** 5337 5338KVM_PV_ENABLE 5339 Allocate memory and register the VM with the Ultravisor, thereby 5340 donating memory to the Ultravisor that will become inaccessible to 5341 KVM. All existing CPUs are converted to protected ones. After this 5342 command has succeeded, any CPU added via hotplug will become 5343 protected during its creation as well. 5344 5345 Errors: 5346 5347 ===== ============================= 5348 EINTR an unmasked signal is pending 5349 ===== ============================= 5350 5351KVM_PV_DISABLE 5352 Deregister the VM from the Ultravisor and reclaim the memory that had 5353 been donated to the Ultravisor, making it usable by the kernel again. 5354 All registered VCPUs are converted back to non-protected ones. If a 5355 previous protected VM had been prepared for asynchronous teardown with 5356 KVM_PV_ASYNC_CLEANUP_PREPARE and not subsequently torn down with 5357 KVM_PV_ASYNC_CLEANUP_PERFORM, it will be torn down in this call 5358 together with the current protected VM. 5359 5360KVM_PV_VM_SET_SEC_PARMS 5361 Pass the image header from VM memory to the Ultravisor in 5362 preparation of image unpacking and verification. 5363 5364KVM_PV_VM_UNPACK 5365 Unpack (protect and decrypt) a page of the encrypted boot image. 5366 5367KVM_PV_VM_VERIFY 5368 Verify the integrity of the unpacked image. Only if this succeeds, 5369 KVM is allowed to start protected VCPUs. 5370 5371KVM_PV_INFO 5372 :Capability: KVM_CAP_S390_PROTECTED_DUMP 5373 5374 Presents an API that provides Ultravisor related data to userspace 5375 via subcommands. len_max is the size of the user space buffer, 5376 len_written is KVM's indication of how much bytes of that buffer 5377 were actually written to. len_written can be used to determine the 5378 valid fields if more response fields are added in the future. 5379 5380 :: 5381 5382 enum pv_cmd_info_id { 5383 KVM_PV_INFO_VM, 5384 KVM_PV_INFO_DUMP, 5385 }; 5386 5387 struct kvm_s390_pv_info_header { 5388 __u32 id; 5389 __u32 len_max; 5390 __u32 len_written; 5391 __u32 reserved; 5392 }; 5393 5394 struct kvm_s390_pv_info { 5395 struct kvm_s390_pv_info_header header; 5396 struct kvm_s390_pv_info_dump dump; 5397 struct kvm_s390_pv_info_vm vm; 5398 }; 5399 5400**subcommands:** 5401 5402 KVM_PV_INFO_VM 5403 This subcommand provides basic Ultravisor information for PV 5404 hosts. These values are likely also exported as files in the sysfs 5405 firmware UV query interface but they are more easily available to 5406 programs in this API. 5407 5408 The installed calls and feature_indication members provide the 5409 installed UV calls and the UV's other feature indications. 5410 5411 The max_* members provide information about the maximum number of PV 5412 vcpus, PV guests and PV guest memory size. 5413 5414 :: 5415 5416 struct kvm_s390_pv_info_vm { 5417 __u64 inst_calls_list[4]; 5418 __u64 max_cpus; 5419 __u64 max_guests; 5420 __u64 max_guest_addr; 5421 __u64 feature_indication; 5422 }; 5423 5424 5425 KVM_PV_INFO_DUMP 5426 This subcommand provides information related to dumping PV guests. 5427 5428 :: 5429 5430 struct kvm_s390_pv_info_dump { 5431 __u64 dump_cpu_buffer_len; 5432 __u64 dump_config_mem_buffer_per_1m; 5433 __u64 dump_config_finalize_len; 5434 }; 5435 5436KVM_PV_DUMP 5437 :Capability: KVM_CAP_S390_PROTECTED_DUMP 5438 5439 Presents an API that provides calls which facilitate dumping a 5440 protected VM. 5441 5442 :: 5443 5444 struct kvm_s390_pv_dmp { 5445 __u64 subcmd; 5446 __u64 buff_addr; 5447 __u64 buff_len; 5448 __u64 gaddr; /* For dump storage state */ 5449 }; 5450 5451 **subcommands:** 5452 5453 KVM_PV_DUMP_INIT 5454 Initializes the dump process of a protected VM. If this call does 5455 not succeed all other subcommands will fail with -EINVAL. This 5456 subcommand will return -EINVAL if a dump process has not yet been 5457 completed. 5458 5459 Not all PV vms can be dumped, the owner needs to set `dump 5460 allowed` PCF bit 34 in the SE header to allow dumping. 5461 5462 KVM_PV_DUMP_CONFIG_STOR_STATE 5463 Stores `buff_len` bytes of tweak component values starting with 5464 the 1MB block specified by the absolute guest address 5465 (`gaddr`). `buff_len` needs to be `conf_dump_storage_state_len` 5466 aligned and at least >= the `conf_dump_storage_state_len` value 5467 provided by the dump uv_info data. buff_user might be written to 5468 even if an error rc is returned. For instance if we encounter a 5469 fault after writing the first page of data. 5470 5471 KVM_PV_DUMP_COMPLETE 5472 If the subcommand succeeds it completes the dump process and lets 5473 KVM_PV_DUMP_INIT be called again. 5474 5475 On success `conf_dump_finalize_len` bytes of completion data will be 5476 stored to the `buff_addr`. The completion data contains a key 5477 derivation seed, IV, tweak nonce and encryption keys as well as an 5478 authentication tag all of which are needed to decrypt the dump at a 5479 later time. 5480 5481KVM_PV_ASYNC_CLEANUP_PREPARE 5482 :Capability: KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 5483 5484 Prepare the current protected VM for asynchronous teardown. Most 5485 resources used by the current protected VM will be set aside for a 5486 subsequent asynchronous teardown. The current protected VM will then 5487 resume execution immediately as non-protected. There can be at most 5488 one protected VM prepared for asynchronous teardown at any time. If 5489 a protected VM had already been prepared for teardown without 5490 subsequently calling KVM_PV_ASYNC_CLEANUP_PERFORM, this call will 5491 fail. In that case, the userspace process should issue a normal 5492 KVM_PV_DISABLE. The resources set aside with this call will need to 5493 be cleaned up with a subsequent call to KVM_PV_ASYNC_CLEANUP_PERFORM 5494 or KVM_PV_DISABLE, otherwise they will be cleaned up when KVM 5495 terminates. KVM_PV_ASYNC_CLEANUP_PREPARE can be called again as soon 5496 as cleanup starts, i.e. before KVM_PV_ASYNC_CLEANUP_PERFORM finishes. 5497 5498KVM_PV_ASYNC_CLEANUP_PERFORM 5499 :Capability: KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 5500 5501 Tear down the protected VM previously prepared for teardown with 5502 KVM_PV_ASYNC_CLEANUP_PREPARE. The resources that had been set aside 5503 will be freed during the execution of this command. This PV command 5504 should ideally be issued by userspace from a separate thread. If a 5505 fatal signal is received (or the process terminates naturally), the 5506 command will terminate immediately without completing, and the normal 5507 KVM shutdown procedure will take care of cleaning up all remaining 5508 protected VMs, including the ones whose teardown was interrupted by 5509 process termination. 5510 55114.126 KVM_XEN_HVM_SET_ATTR 5512-------------------------- 5513 5514:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO 5515:Architectures: x86 5516:Type: vm ioctl 5517:Parameters: struct kvm_xen_hvm_attr 5518:Returns: 0 on success, < 0 on error 5519 5520:: 5521 5522 struct kvm_xen_hvm_attr { 5523 __u16 type; 5524 __u16 pad[3]; 5525 union { 5526 __u8 long_mode; 5527 __u8 vector; 5528 __u8 runstate_update_flag; 5529 union { 5530 __u64 gfn; 5531 __u64 hva; 5532 } shared_info; 5533 struct { 5534 __u32 send_port; 5535 __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ 5536 __u32 flags; 5537 union { 5538 struct { 5539 __u32 port; 5540 __u32 vcpu; 5541 __u32 priority; 5542 } port; 5543 struct { 5544 __u32 port; /* Zero for eventfd */ 5545 __s32 fd; 5546 } eventfd; 5547 __u32 padding[4]; 5548 } deliver; 5549 } evtchn; 5550 __u32 xen_version; 5551 __u64 pad[8]; 5552 } u; 5553 }; 5554 5555type values: 5556 5557KVM_XEN_ATTR_TYPE_LONG_MODE 5558 Sets the ABI mode of the VM to 32-bit or 64-bit (long mode). This 5559 determines the layout of the shared_info page exposed to the VM. 5560 5561KVM_XEN_ATTR_TYPE_SHARED_INFO 5562 Sets the guest physical frame number at which the Xen shared_info 5563 page resides. Note that although Xen places vcpu_info for the first 5564 32 vCPUs in the shared_info page, KVM does not automatically do so 5565 and instead requires that KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO or 5566 KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA be used explicitly even when 5567 the vcpu_info for a given vCPU resides at the "default" location 5568 in the shared_info page. This is because KVM may not be aware of 5569 the Xen CPU id which is used as the index into the vcpu_info[] 5570 array, so may know the correct default location. 5571 5572 Note that the shared_info page may be constantly written to by KVM; 5573 it contains the event channel bitmap used to deliver interrupts to 5574 a Xen guest, amongst other things. It is exempt from dirty tracking 5575 mechanisms — KVM will not explicitly mark the page as dirty each 5576 time an event channel interrupt is delivered to the guest! Thus, 5577 userspace should always assume that the designated GFN is dirty if 5578 any vCPU has been running or any event channel interrupts can be 5579 routed to the guest. 5580 5581 Setting the gfn to KVM_XEN_INVALID_GFN will disable the shared_info 5582 page. 5583 5584KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA 5585 If the KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA flag is also set in the 5586 Xen capabilities, then this attribute may be used to set the 5587 userspace address at which the shared_info page resides, which 5588 will always be fixed in the VMM regardless of where it is mapped 5589 in guest physical address space. This attribute should be used in 5590 preference to KVM_XEN_ATTR_TYPE_SHARED_INFO as it avoids 5591 unnecessary invalidation of an internal cache when the page is 5592 re-mapped in guest physical address space. 5593 5594 Setting the hva to zero will disable the shared_info page. 5595 5596KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 5597 Sets the exception vector used to deliver Xen event channel upcalls. 5598 This is the HVM-wide vector injected directly by the hypervisor 5599 (not through the local APIC), typically configured by a guest via 5600 HVM_PARAM_CALLBACK_IRQ. This can be disabled again (e.g. for guest 5601 SHUTDOWN_soft_reset) by setting it to zero. 5602 5603KVM_XEN_ATTR_TYPE_EVTCHN 5604 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates 5605 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures 5606 an outbound port number for interception of EVTCHNOP_send requests 5607 from the guest. A given sending port number may be directed back to 5608 a specified vCPU (by APIC ID) / port / priority on the guest, or to 5609 trigger events on an eventfd. The vCPU and priority can be changed 5610 by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, but other 5611 fields cannot change for a given sending port. A port mapping is 5612 removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags field. Passing 5613 KVM_XEN_EVTCHN_RESET in the flags field removes all interception of 5614 outbound event channels. The values of the flags field are mutually 5615 exclusive and cannot be combined as a bitmask. 5616 5617KVM_XEN_ATTR_TYPE_XEN_VERSION 5618 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates 5619 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures 5620 the 32-bit version code returned to the guest when it invokes the 5621 XENVER_version call; typically (XEN_MAJOR << 16 | XEN_MINOR). PV 5622 Xen guests will often use this to as a dummy hypercall to trigger 5623 event channel delivery, so responding within the kernel without 5624 exiting to userspace is beneficial. 5625 5626KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 5627 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates 5628 support for KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG. It enables the 5629 XEN_RUNSTATE_UPDATE flag which allows guest vCPUs to safely read 5630 other vCPUs' vcpu_runstate_info. Xen guests enable this feature via 5631 the VMASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist 5632 hypercall. 5633 56344.127 KVM_XEN_HVM_GET_ATTR 5635-------------------------- 5636 5637:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO 5638:Architectures: x86 5639:Type: vm ioctl 5640:Parameters: struct kvm_xen_hvm_attr 5641:Returns: 0 on success, < 0 on error 5642 5643Allows Xen VM attributes to be read. For the structure and types, 5644see KVM_XEN_HVM_SET_ATTR above. The KVM_XEN_ATTR_TYPE_EVTCHN 5645attribute cannot be read. 5646 56474.128 KVM_XEN_VCPU_SET_ATTR 5648--------------------------- 5649 5650:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO 5651:Architectures: x86 5652:Type: vcpu ioctl 5653:Parameters: struct kvm_xen_vcpu_attr 5654:Returns: 0 on success, < 0 on error 5655 5656:: 5657 5658 struct kvm_xen_vcpu_attr { 5659 __u16 type; 5660 __u16 pad[3]; 5661 union { 5662 __u64 gpa; 5663 __u64 pad[4]; 5664 struct { 5665 __u64 state; 5666 __u64 state_entry_time; 5667 __u64 time_running; 5668 __u64 time_runnable; 5669 __u64 time_blocked; 5670 __u64 time_offline; 5671 } runstate; 5672 __u32 vcpu_id; 5673 struct { 5674 __u32 port; 5675 __u32 priority; 5676 __u64 expires_ns; 5677 } timer; 5678 __u8 vector; 5679 } u; 5680 }; 5681 5682type values: 5683 5684KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 5685 Sets the guest physical address of the vcpu_info for a given vCPU. 5686 As with the shared_info page for the VM, the corresponding page may be 5687 dirtied at any time if event channel interrupt delivery is enabled, so 5688 userspace should always assume that the page is dirty without relying 5689 on dirty logging. Setting the gpa to KVM_XEN_INVALID_GPA will disable 5690 the vcpu_info. 5691 5692KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA 5693 If the KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA flag is also set in the 5694 Xen capabilities, then this attribute may be used to set the 5695 userspace address of the vcpu_info for a given vCPU. It should 5696 only be used when the vcpu_info resides at the "default" location 5697 in the shared_info page. In this case it is safe to assume the 5698 userspace address will not change, because the shared_info page is 5699 an overlay on guest memory and remains at a fixed host address 5700 regardless of where it is mapped in guest physical address space 5701 and hence unnecessary invalidation of an internal cache may be 5702 avoided if the guest memory layout is modified. 5703 If the vcpu_info does not reside at the "default" location then 5704 it is not guaranteed to remain at the same host address and 5705 hence the aforementioned cache invalidation is required. 5706 5707KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 5708 Sets the guest physical address of an additional pvclock structure 5709 for a given vCPU. This is typically used for guest vsyscall support. 5710 Setting the gpa to KVM_XEN_INVALID_GPA will disable the structure. 5711 5712KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 5713 Sets the guest physical address of the vcpu_runstate_info for a given 5714 vCPU. This is how a Xen guest tracks CPU state such as steal time. 5715 Setting the gpa to KVM_XEN_INVALID_GPA will disable the runstate area. 5716 5717KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 5718 Sets the runstate (RUNSTATE_running/_runnable/_blocked/_offline) of 5719 the given vCPU from the .u.runstate.state member of the structure. 5720 KVM automatically accounts running and runnable time but blocked 5721 and offline states are only entered explicitly. 5722 5723KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 5724 Sets all fields of the vCPU runstate data from the .u.runstate member 5725 of the structure, including the current runstate. The state_entry_time 5726 must equal the sum of the other four times. 5727 5728KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 5729 This *adds* the contents of the .u.runstate members of the structure 5730 to the corresponding members of the given vCPU's runstate data, thus 5731 permitting atomic adjustments to the runstate times. The adjustment 5732 to the state_entry_time must equal the sum of the adjustments to the 5733 other four times. The state field must be set to -1, or to a valid 5734 runstate value (RUNSTATE_running, RUNSTATE_runnable, RUNSTATE_blocked 5735 or RUNSTATE_offline) to set the current accounted state as of the 5736 adjusted state_entry_time. 5737 5738KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 5739 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates 5740 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the Xen 5741 vCPU ID of the given vCPU, to allow timer-related VCPU operations to 5742 be intercepted by KVM. 5743 5744KVM_XEN_VCPU_ATTR_TYPE_TIMER 5745 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates 5746 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the 5747 event channel port/priority for the VIRQ_TIMER of the vCPU, as well 5748 as allowing a pending timer to be saved/restored. Setting the timer 5749 port to zero disables kernel handling of the singleshot timer. 5750 5751KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 5752 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates 5753 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the 5754 per-vCPU local APIC upcall vector, configured by a Xen guest with 5755 the HVMOP_set_evtchn_upcall_vector hypercall. This is typically 5756 used by Windows guests, and is distinct from the HVM-wide upcall 5757 vector configured with HVM_PARAM_CALLBACK_IRQ. It is disabled by 5758 setting the vector to zero. 5759 5760 57614.129 KVM_XEN_VCPU_GET_ATTR 5762--------------------------- 5763 5764:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO 5765:Architectures: x86 5766:Type: vcpu ioctl 5767:Parameters: struct kvm_xen_vcpu_attr 5768:Returns: 0 on success, < 0 on error 5769 5770Allows Xen vCPU attributes to be read. For the structure and types, 5771see KVM_XEN_VCPU_SET_ATTR above. 5772 5773The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST type may not be used 5774with the KVM_XEN_VCPU_GET_ATTR ioctl. 5775 57764.130 KVM_ARM_MTE_COPY_TAGS 5777--------------------------- 5778 5779:Capability: KVM_CAP_ARM_MTE 5780:Architectures: arm64 5781:Type: vm ioctl 5782:Parameters: struct kvm_arm_copy_mte_tags 5783:Returns: number of bytes copied, < 0 on error (-EINVAL for incorrect 5784 arguments, -EFAULT if memory cannot be accessed). 5785 5786:: 5787 5788 struct kvm_arm_copy_mte_tags { 5789 __u64 guest_ipa; 5790 __u64 length; 5791 void __user *addr; 5792 __u64 flags; 5793 __u64 reserved[2]; 5794 }; 5795 5796Copies Memory Tagging Extension (MTE) tags to/from guest tag memory. The 5797``guest_ipa`` and ``length`` fields must be ``PAGE_SIZE`` aligned. 5798``length`` must not be bigger than 2^31 - PAGE_SIZE bytes. The ``addr`` 5799field must point to a buffer which the tags will be copied to or from. 5800 5801``flags`` specifies the direction of copy, either ``KVM_ARM_TAGS_TO_GUEST`` or 5802``KVM_ARM_TAGS_FROM_GUEST``. 5803 5804The size of the buffer to store the tags is ``(length / 16)`` bytes 5805(granules in MTE are 16 bytes long). Each byte contains a single tag 5806value. This matches the format of ``PTRACE_PEEKMTETAGS`` and 5807``PTRACE_POKEMTETAGS``. 5808 5809If an error occurs before any data is copied then a negative error code is 5810returned. If some tags have been copied before an error occurs then the number 5811of bytes successfully copied is returned. If the call completes successfully 5812then ``length`` is returned. 5813 58144.131 KVM_GET_SREGS2 5815-------------------- 5816 5817:Capability: KVM_CAP_SREGS2 5818:Architectures: x86 5819:Type: vcpu ioctl 5820:Parameters: struct kvm_sregs2 (out) 5821:Returns: 0 on success, -1 on error 5822 5823Reads special registers from the vcpu. 5824This ioctl (when supported) replaces the KVM_GET_SREGS. 5825 5826:: 5827 5828 struct kvm_sregs2 { 5829 /* out (KVM_GET_SREGS2) / in (KVM_SET_SREGS2) */ 5830 struct kvm_segment cs, ds, es, fs, gs, ss; 5831 struct kvm_segment tr, ldt; 5832 struct kvm_dtable gdt, idt; 5833 __u64 cr0, cr2, cr3, cr4, cr8; 5834 __u64 efer; 5835 __u64 apic_base; 5836 __u64 flags; 5837 __u64 pdptrs[4]; 5838 }; 5839 5840flags values for ``kvm_sregs2``: 5841 5842``KVM_SREGS2_FLAGS_PDPTRS_VALID`` 5843 5844 Indicates that the struct contains valid PDPTR values. 5845 5846 58474.132 KVM_SET_SREGS2 5848-------------------- 5849 5850:Capability: KVM_CAP_SREGS2 5851:Architectures: x86 5852:Type: vcpu ioctl 5853:Parameters: struct kvm_sregs2 (in) 5854:Returns: 0 on success, -1 on error 5855 5856Writes special registers into the vcpu. 5857See KVM_GET_SREGS2 for the data structures. 5858This ioctl (when supported) replaces the KVM_SET_SREGS. 5859 58604.133 KVM_GET_STATS_FD 5861---------------------- 5862 5863:Capability: KVM_CAP_STATS_BINARY_FD 5864:Architectures: all 5865:Type: vm ioctl, vcpu ioctl 5866:Parameters: none 5867:Returns: statistics file descriptor on success, < 0 on error 5868 5869Errors: 5870 5871 ====== ====================================================== 5872 ENOMEM if the fd could not be created due to lack of memory 5873 EMFILE if the number of opened files exceeds the limit 5874 ====== ====================================================== 5875 5876The returned file descriptor can be used to read VM/vCPU statistics data in 5877binary format. The data in the file descriptor consists of four blocks 5878organized as follows: 5879 5880+-------------+ 5881| Header | 5882+-------------+ 5883| id string | 5884+-------------+ 5885| Descriptors | 5886+-------------+ 5887| Stats Data | 5888+-------------+ 5889 5890Apart from the header starting at offset 0, please be aware that it is 5891not guaranteed that the four blocks are adjacent or in the above order; 5892the offsets of the id, descriptors and data blocks are found in the 5893header. However, all four blocks are aligned to 64 bit offsets in the 5894file and they do not overlap. 5895 5896All blocks except the data block are immutable. Userspace can read them 5897only one time after retrieving the file descriptor, and then use ``pread`` or 5898``lseek`` to read the statistics repeatedly. 5899 5900All data is in system endianness. 5901 5902The format of the header is as follows:: 5903 5904 struct kvm_stats_header { 5905 __u32 flags; 5906 __u32 name_size; 5907 __u32 num_desc; 5908 __u32 id_offset; 5909 __u32 desc_offset; 5910 __u32 data_offset; 5911 }; 5912 5913The ``flags`` field is not used at the moment. It is always read as 0. 5914 5915The ``name_size`` field is the size (in byte) of the statistics name string 5916(including trailing '\0') which is contained in the "id string" block and 5917appended at the end of every descriptor. 5918 5919The ``num_desc`` field is the number of descriptors that are included in the 5920descriptor block. (The actual number of values in the data block may be 5921larger, since each descriptor may comprise more than one value). 5922 5923The ``id_offset`` field is the offset of the id string from the start of the 5924file indicated by the file descriptor. It is a multiple of 8. 5925 5926The ``desc_offset`` field is the offset of the Descriptors block from the start 5927of the file indicated by the file descriptor. It is a multiple of 8. 5928 5929The ``data_offset`` field is the offset of the Stats Data block from the start 5930of the file indicated by the file descriptor. It is a multiple of 8. 5931 5932The id string block contains a string which identifies the file descriptor on 5933which KVM_GET_STATS_FD was invoked. The size of the block, including the 5934trailing ``'\0'``, is indicated by the ``name_size`` field in the header. 5935 5936The descriptors block is only needed to be read once for the lifetime of the 5937file descriptor contains a sequence of ``struct kvm_stats_desc``, each followed 5938by a string of size ``name_size``. 5939:: 5940 5941 #define KVM_STATS_TYPE_SHIFT 0 5942 #define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT) 5943 #define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) 5944 #define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) 5945 #define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT) 5946 #define KVM_STATS_TYPE_LINEAR_HIST (0x3 << KVM_STATS_TYPE_SHIFT) 5947 #define KVM_STATS_TYPE_LOG_HIST (0x4 << KVM_STATS_TYPE_SHIFT) 5948 #define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_LOG_HIST 5949 5950 #define KVM_STATS_UNIT_SHIFT 4 5951 #define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) 5952 #define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT) 5953 #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) 5954 #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) 5955 #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) 5956 #define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT) 5957 #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_BOOLEAN 5958 5959 #define KVM_STATS_BASE_SHIFT 8 5960 #define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) 5961 #define KVM_STATS_BASE_POW10 (0x0 << KVM_STATS_BASE_SHIFT) 5962 #define KVM_STATS_BASE_POW2 (0x1 << KVM_STATS_BASE_SHIFT) 5963 #define KVM_STATS_BASE_MAX KVM_STATS_BASE_POW2 5964 5965 struct kvm_stats_desc { 5966 __u32 flags; 5967 __s16 exponent; 5968 __u16 size; 5969 __u32 offset; 5970 __u32 bucket_size; 5971 char name[]; 5972 }; 5973 5974The ``flags`` field contains the type and unit of the statistics data described 5975by this descriptor. Its endianness is CPU native. 5976The following flags are supported: 5977 5978Bits 0-3 of ``flags`` encode the type: 5979 5980 * ``KVM_STATS_TYPE_CUMULATIVE`` 5981 The statistics reports a cumulative count. The value of data can only be increased. 5982 Most of the counters used in KVM are of this type. 5983 The corresponding ``size`` field for this type is always 1. 5984 All cumulative statistics data are read/write. 5985 * ``KVM_STATS_TYPE_INSTANT`` 5986 The statistics reports an instantaneous value. Its value can be increased or 5987 decreased. This type is usually used as a measurement of some resources, 5988 like the number of dirty pages, the number of large pages, etc. 5989 All instant statistics are read only. 5990 The corresponding ``size`` field for this type is always 1. 5991 * ``KVM_STATS_TYPE_PEAK`` 5992 The statistics data reports a peak value, for example the maximum number 5993 of items in a hash table bucket, the longest time waited and so on. 5994 The value of data can only be increased. 5995 The corresponding ``size`` field for this type is always 1. 5996 * ``KVM_STATS_TYPE_LINEAR_HIST`` 5997 The statistic is reported as a linear histogram. The number of 5998 buckets is specified by the ``size`` field. The size of buckets is specified 5999 by the ``hist_param`` field. The range of the Nth bucket (1 <= N < ``size``) 6000 is [``hist_param``*(N-1), ``hist_param``*N), while the range of the last 6001 bucket is [``hist_param``*(``size``-1), +INF). (+INF means positive infinity 6002 value.) 6003 * ``KVM_STATS_TYPE_LOG_HIST`` 6004 The statistic is reported as a logarithmic histogram. The number of 6005 buckets is specified by the ``size`` field. The range of the first bucket is 6006 [0, 1), while the range of the last bucket is [pow(2, ``size``-2), +INF). 6007 Otherwise, The Nth bucket (1 < N < ``size``) covers 6008 [pow(2, N-2), pow(2, N-1)). 6009 6010Bits 4-7 of ``flags`` encode the unit: 6011 6012 * ``KVM_STATS_UNIT_NONE`` 6013 There is no unit for the value of statistics data. This usually means that 6014 the value is a simple counter of an event. 6015 * ``KVM_STATS_UNIT_BYTES`` 6016 It indicates that the statistics data is used to measure memory size, in the 6017 unit of Byte, KiByte, MiByte, GiByte, etc. The unit of the data is 6018 determined by the ``exponent`` field in the descriptor. 6019 * ``KVM_STATS_UNIT_SECONDS`` 6020 It indicates that the statistics data is used to measure time or latency. 6021 * ``KVM_STATS_UNIT_CYCLES`` 6022 It indicates that the statistics data is used to measure CPU clock cycles. 6023 * ``KVM_STATS_UNIT_BOOLEAN`` 6024 It indicates that the statistic will always be either 0 or 1. Boolean 6025 statistics of "peak" type will never go back from 1 to 0. Boolean 6026 statistics can be linear histograms (with two buckets) but not logarithmic 6027 histograms. 6028 6029Note that, in the case of histograms, the unit applies to the bucket 6030ranges, while the bucket value indicates how many samples fell in the 6031bucket's range. 6032 6033Bits 8-11 of ``flags``, together with ``exponent``, encode the scale of the 6034unit: 6035 6036 * ``KVM_STATS_BASE_POW10`` 6037 The scale is based on power of 10. It is used for measurement of time and 6038 CPU clock cycles. For example, an exponent of -9 can be used with 6039 ``KVM_STATS_UNIT_SECONDS`` to express that the unit is nanoseconds. 6040 * ``KVM_STATS_BASE_POW2`` 6041 The scale is based on power of 2. It is used for measurement of memory size. 6042 For example, an exponent of 20 can be used with ``KVM_STATS_UNIT_BYTES`` to 6043 express that the unit is MiB. 6044 6045The ``size`` field is the number of values of this statistics data. Its 6046value is usually 1 for most of simple statistics. 1 means it contains an 6047unsigned 64bit data. 6048 6049The ``offset`` field is the offset from the start of Data Block to the start of 6050the corresponding statistics data. 6051 6052The ``bucket_size`` field is used as a parameter for histogram statistics data. 6053It is only used by linear histogram statistics data, specifying the size of a 6054bucket in the unit expressed by bits 4-11 of ``flags`` together with ``exponent``. 6055 6056The ``name`` field is the name string of the statistics data. The name string 6057starts at the end of ``struct kvm_stats_desc``. The maximum length including 6058the trailing ``'\0'``, is indicated by ``name_size`` in the header. 6059 6060The Stats Data block contains an array of 64-bit values in the same order 6061as the descriptors in Descriptors block. 6062 60634.134 KVM_GET_XSAVE2 6064-------------------- 6065 6066:Capability: KVM_CAP_XSAVE2 6067:Architectures: x86 6068:Type: vcpu ioctl 6069:Parameters: struct kvm_xsave (out) 6070:Returns: 0 on success, -1 on error 6071 6072 6073:: 6074 6075 struct kvm_xsave { 6076 __u32 region[1024]; 6077 __u32 extra[0]; 6078 }; 6079 6080This ioctl would copy current vcpu's xsave struct to the userspace. It 6081copies as many bytes as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) 6082when invoked on the vm file descriptor. The size value returned by 6083KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) will always be at least 4096. 6084Currently, it is only greater than 4096 if a dynamic feature has been 6085enabled with ``arch_prctl()``, but this may change in the future. 6086 6087The offsets of the state save areas in struct kvm_xsave follow the contents 6088of CPUID leaf 0xD on the host. 6089 60904.135 KVM_XEN_HVM_EVTCHN_SEND 6091----------------------------- 6092 6093:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND 6094:Architectures: x86 6095:Type: vm ioctl 6096:Parameters: struct kvm_irq_routing_xen_evtchn 6097:Returns: 0 on success, < 0 on error 6098 6099 6100:: 6101 6102 struct kvm_irq_routing_xen_evtchn { 6103 __u32 port; 6104 __u32 vcpu; 6105 __u32 priority; 6106 }; 6107 6108This ioctl injects an event channel interrupt directly to the guest vCPU. 6109 61104.136 KVM_S390_PV_CPU_COMMAND 6111----------------------------- 6112 6113:Capability: KVM_CAP_S390_PROTECTED_DUMP 6114:Architectures: s390 6115:Type: vcpu ioctl 6116:Parameters: none 6117:Returns: 0 on success, < 0 on error 6118 6119This ioctl closely mirrors `KVM_S390_PV_COMMAND` but handles requests 6120for vcpus. It re-uses the kvm_s390_pv_dmp struct and hence also shares 6121the command ids. 6122 6123**command:** 6124 6125KVM_PV_DUMP 6126 Presents an API that provides calls which facilitate dumping a vcpu 6127 of a protected VM. 6128 6129**subcommand:** 6130 6131KVM_PV_DUMP_CPU 6132 Provides encrypted dump data like register values. 6133 The length of the returned data is provided by uv_info.guest_cpu_stor_len. 6134 61354.137 KVM_S390_ZPCI_OP 6136---------------------- 6137 6138:Capability: KVM_CAP_S390_ZPCI_OP 6139:Architectures: s390 6140:Type: vm ioctl 6141:Parameters: struct kvm_s390_zpci_op (in) 6142:Returns: 0 on success, <0 on error 6143 6144Used to manage hardware-assisted virtualization features for zPCI devices. 6145 6146Parameters are specified via the following structure:: 6147 6148 struct kvm_s390_zpci_op { 6149 /* in */ 6150 __u32 fh; /* target device */ 6151 __u8 op; /* operation to perform */ 6152 __u8 pad[3]; 6153 union { 6154 /* for KVM_S390_ZPCIOP_REG_AEN */ 6155 struct { 6156 __u64 ibv; /* Guest addr of interrupt bit vector */ 6157 __u64 sb; /* Guest addr of summary bit */ 6158 __u32 flags; 6159 __u32 noi; /* Number of interrupts */ 6160 __u8 isc; /* Guest interrupt subclass */ 6161 __u8 sbo; /* Offset of guest summary bit vector */ 6162 __u16 pad; 6163 } reg_aen; 6164 __u64 reserved[8]; 6165 } u; 6166 }; 6167 6168The type of operation is specified in the "op" field. 6169KVM_S390_ZPCIOP_REG_AEN is used to register the VM for adapter event 6170notification interpretation, which will allow firmware delivery of adapter 6171events directly to the vm, with KVM providing a backup delivery mechanism; 6172KVM_S390_ZPCIOP_DEREG_AEN is used to subsequently disable interpretation of 6173adapter event notifications. 6174 6175The target zPCI function must also be specified via the "fh" field. For the 6176KVM_S390_ZPCIOP_REG_AEN operation, additional information to establish firmware 6177delivery must be provided via the "reg_aen" struct. 6178 6179The "pad" and "reserved" fields may be used for future extensions and should be 6180set to 0s by userspace. 6181 61824.138 KVM_ARM_SET_COUNTER_OFFSET 6183-------------------------------- 6184 6185:Capability: KVM_CAP_COUNTER_OFFSET 6186:Architectures: arm64 6187:Type: vm ioctl 6188:Parameters: struct kvm_arm_counter_offset (in) 6189:Returns: 0 on success, < 0 on error 6190 6191This capability indicates that userspace is able to apply a single VM-wide 6192offset to both the virtual and physical counters as viewed by the guest 6193using the KVM_ARM_SET_CNT_OFFSET ioctl and the following data structure: 6194 6195:: 6196 6197 struct kvm_arm_counter_offset { 6198 __u64 counter_offset; 6199 __u64 reserved; 6200 }; 6201 6202The offset describes a number of counter cycles that are subtracted from 6203both virtual and physical counter views (similar to the effects of the 6204CNTVOFF_EL2 and CNTPOFF_EL2 system registers, but only global). The offset 6205always applies to all vcpus (already created or created after this ioctl) 6206for this VM. 6207 6208It is userspace's responsibility to compute the offset based, for example, 6209on previous values of the guest counters. 6210 6211Any value other than 0 for the "reserved" field may result in an error 6212(-EINVAL) being returned. This ioctl can also return -EBUSY if any vcpu 6213ioctl is issued concurrently. 6214 6215Note that using this ioctl results in KVM ignoring subsequent userspace 6216writes to the CNTVCT_EL0 and CNTPCT_EL0 registers using the SET_ONE_REG 6217interface. No error will be returned, but the resulting offset will not be 6218applied. 6219 6220.. _KVM_ARM_GET_REG_WRITABLE_MASKS: 6221 62224.139 KVM_ARM_GET_REG_WRITABLE_MASKS 6223------------------------------------ 6224 6225:Capability: KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 6226:Architectures: arm64 6227:Type: vm ioctl 6228:Parameters: struct reg_mask_range (in/out) 6229:Returns: 0 on success, < 0 on error 6230 6231 6232:: 6233 6234 #define KVM_ARM_FEATURE_ID_RANGE 0 6235 #define KVM_ARM_FEATURE_ID_RANGE_SIZE (3 * 8 * 8) 6236 6237 struct reg_mask_range { 6238 __u64 addr; /* Pointer to mask array */ 6239 __u32 range; /* Requested range */ 6240 __u32 reserved[13]; 6241 }; 6242 6243This ioctl copies the writable masks for a selected range of registers to 6244userspace. 6245 6246The ``addr`` field is a pointer to the destination array where KVM copies 6247the writable masks. 6248 6249The ``range`` field indicates the requested range of registers. 6250``KVM_CHECK_EXTENSION`` for the ``KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES`` 6251capability returns the supported ranges, expressed as a set of flags. Each 6252flag's bit index represents a possible value for the ``range`` field. 6253All other values are reserved for future use and KVM may return an error. 6254 6255The ``reserved[13]`` array is reserved for future use and should be 0, or 6256KVM may return an error. 6257 6258KVM_ARM_FEATURE_ID_RANGE (0) 6259^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 6260 6261The Feature ID range is defined as the AArch64 System register space with 6262op0==3, op1=={0, 1, 3}, CRn==0, CRm=={0-7}, op2=={0-7}. 6263 6264The mask returned array pointed to by ``addr`` is indexed by the macro 6265``ARM64_FEATURE_ID_RANGE_IDX(op0, op1, crn, crm, op2)``, allowing userspace 6266to know what fields can be changed for the system register described by 6267``op0, op1, crn, crm, op2``. KVM rejects ID register values that describe a 6268superset of the features supported by the system. 6269 62704.140 KVM_SET_USER_MEMORY_REGION2 6271--------------------------------- 6272 6273:Capability: KVM_CAP_USER_MEMORY2 6274:Architectures: all 6275:Type: vm ioctl 6276:Parameters: struct kvm_userspace_memory_region2 (in) 6277:Returns: 0 on success, -1 on error 6278 6279KVM_SET_USER_MEMORY_REGION2 is an extension to KVM_SET_USER_MEMORY_REGION that 6280allows mapping guest_memfd memory into a guest. All fields shared with 6281KVM_SET_USER_MEMORY_REGION identically. Userspace can set KVM_MEM_GUEST_MEMFD 6282in flags to have KVM bind the memory region to a given guest_memfd range of 6283[guest_memfd_offset, guest_memfd_offset + memory_size]. The target guest_memfd 6284must point at a file created via KVM_CREATE_GUEST_MEMFD on the current VM, and 6285the target range must not be bound to any other memory region. All standard 6286bounds checks apply (use common sense). 6287 6288:: 6289 6290 struct kvm_userspace_memory_region2 { 6291 __u32 slot; 6292 __u32 flags; 6293 __u64 guest_phys_addr; 6294 __u64 memory_size; /* bytes */ 6295 __u64 userspace_addr; /* start of the userspace allocated memory */ 6296 __u64 guest_memfd_offset; 6297 __u32 guest_memfd; 6298 __u32 pad1; 6299 __u64 pad2[14]; 6300 }; 6301 6302A KVM_MEM_GUEST_MEMFD region _must_ have a valid guest_memfd (private memory) and 6303userspace_addr (shared memory). However, "valid" for userspace_addr simply 6304means that the address itself must be a legal userspace address. The backing 6305mapping for userspace_addr is not required to be valid/populated at the time of 6306KVM_SET_USER_MEMORY_REGION2, e.g. shared memory can be lazily mapped/allocated 6307on-demand. 6308 6309When mapping a gfn into the guest, KVM selects shared vs. private, i.e consumes 6310userspace_addr vs. guest_memfd, based on the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE 6311state. At VM creation time, all memory is shared, i.e. the PRIVATE attribute 6312is '0' for all gfns. Userspace can control whether memory is shared/private by 6313toggling KVM_MEMORY_ATTRIBUTE_PRIVATE via KVM_SET_MEMORY_ATTRIBUTES as needed. 6314 6315S390: 6316^^^^^ 6317 6318Returns -EINVAL if the VM has the KVM_VM_S390_UCONTROL flag set. 6319Returns -EINVAL if called on a protected VM. 6320 63214.141 KVM_SET_MEMORY_ATTRIBUTES 6322------------------------------- 6323 6324:Capability: KVM_CAP_MEMORY_ATTRIBUTES 6325:Architectures: x86 6326:Type: vm ioctl 6327:Parameters: struct kvm_memory_attributes (in) 6328:Returns: 0 on success, <0 on error 6329 6330KVM_SET_MEMORY_ATTRIBUTES allows userspace to set memory attributes for a range 6331of guest physical memory. 6332 6333:: 6334 6335 struct kvm_memory_attributes { 6336 __u64 address; 6337 __u64 size; 6338 __u64 attributes; 6339 __u64 flags; 6340 }; 6341 6342 #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) 6343 6344The address and size must be page aligned. The supported attributes can be 6345retrieved via ioctl(KVM_CHECK_EXTENSION) on KVM_CAP_MEMORY_ATTRIBUTES. If 6346executed on a VM, KVM_CAP_MEMORY_ATTRIBUTES precisely returns the attributes 6347supported by that VM. If executed at system scope, KVM_CAP_MEMORY_ATTRIBUTES 6348returns all attributes supported by KVM. The only attribute defined at this 6349time is KVM_MEMORY_ATTRIBUTE_PRIVATE, which marks the associated gfn as being 6350guest private memory. 6351 6352Note, there is no "get" API. Userspace is responsible for explicitly tracking 6353the state of a gfn/page as needed. 6354 6355The "flags" field is reserved for future extensions and must be '0'. 6356 63574.142 KVM_CREATE_GUEST_MEMFD 6358---------------------------- 6359 6360:Capability: KVM_CAP_GUEST_MEMFD 6361:Architectures: none 6362:Type: vm ioctl 6363:Parameters: struct kvm_create_guest_memfd(in) 6364:Returns: A file descriptor on success, <0 on error 6365 6366KVM_CREATE_GUEST_MEMFD creates an anonymous file and returns a file descriptor 6367that refers to it. guest_memfd files are roughly analogous to files created 6368via memfd_create(), e.g. guest_memfd files live in RAM, have volatile storage, 6369and are automatically released when the last reference is dropped. Unlike 6370"regular" memfd_create() files, guest_memfd files are bound to their owning 6371virtual machine (see below), cannot be mapped, read, or written by userspace, 6372and cannot be resized (guest_memfd files do however support PUNCH_HOLE). 6373 6374:: 6375 6376 struct kvm_create_guest_memfd { 6377 __u64 size; 6378 __u64 flags; 6379 __u64 reserved[6]; 6380 }; 6381 6382Conceptually, the inode backing a guest_memfd file represents physical memory, 6383i.e. is coupled to the virtual machine as a thing, not to a "struct kvm". The 6384file itself, which is bound to a "struct kvm", is that instance's view of the 6385underlying memory, e.g. effectively provides the translation of guest addresses 6386to host memory. This allows for use cases where multiple KVM structures are 6387used to manage a single virtual machine, e.g. when performing intrahost 6388migration of a virtual machine. 6389 6390KVM currently only supports mapping guest_memfd via KVM_SET_USER_MEMORY_REGION2, 6391and more specifically via the guest_memfd and guest_memfd_offset fields in 6392"struct kvm_userspace_memory_region2", where guest_memfd_offset is the offset 6393into the guest_memfd instance. For a given guest_memfd file, there can be at 6394most one mapping per page, i.e. binding multiple memory regions to a single 6395guest_memfd range is not allowed (any number of memory regions can be bound to 6396a single guest_memfd file, but the bound ranges must not overlap). 6397 6398See KVM_SET_USER_MEMORY_REGION2 for additional details. 6399 64004.143 KVM_PRE_FAULT_MEMORY 6401--------------------------- 6402 6403:Capability: KVM_CAP_PRE_FAULT_MEMORY 6404:Architectures: none 6405:Type: vcpu ioctl 6406:Parameters: struct kvm_pre_fault_memory (in/out) 6407:Returns: 0 if at least one page is processed, < 0 on error 6408 6409Errors: 6410 6411 ========== =============================================================== 6412 EINVAL The specified `gpa` and `size` were invalid (e.g. not 6413 page aligned, causes an overflow, or size is zero). 6414 ENOENT The specified `gpa` is outside defined memslots. 6415 EINTR An unmasked signal is pending and no page was processed. 6416 EFAULT The parameter address was invalid. 6417 EOPNOTSUPP Mapping memory for a GPA is unsupported by the 6418 hypervisor, and/or for the current vCPU state/mode. 6419 EIO unexpected error conditions (also causes a WARN) 6420 ========== =============================================================== 6421 6422:: 6423 6424 struct kvm_pre_fault_memory { 6425 /* in/out */ 6426 __u64 gpa; 6427 __u64 size; 6428 /* in */ 6429 __u64 flags; 6430 __u64 padding[5]; 6431 }; 6432 6433KVM_PRE_FAULT_MEMORY populates KVM's stage-2 page tables used to map memory 6434for the current vCPU state. KVM maps memory as if the vCPU generated a 6435stage-2 read page fault, e.g. faults in memory as needed, but doesn't break 6436CoW. However, KVM does not mark any newly created stage-2 PTE as Accessed. 6437 6438In the case of confidential VM types where there is an initial set up of 6439private guest memory before the guest is 'finalized'/measured, this ioctl 6440should only be issued after completing all the necessary setup to put the 6441guest into a 'finalized' state so that the above semantics can be reliably 6442ensured. 6443 6444In some cases, multiple vCPUs might share the page tables. In this 6445case, the ioctl can be called in parallel. 6446 6447When the ioctl returns, the input values are updated to point to the 6448remaining range. If `size` > 0 on return, the caller can just issue 6449the ioctl again with the same `struct kvm_map_memory` argument. 6450 6451Shadow page tables cannot support this ioctl because they 6452are indexed by virtual address or nested guest physical address. 6453Calling this ioctl when the guest is using shadow page tables (for 6454example because it is running a nested guest with nested page tables) 6455will fail with `EOPNOTSUPP` even if `KVM_CHECK_EXTENSION` reports 6456the capability to be present. 6457 6458`flags` must currently be zero. 6459 6460 6461.. _kvm_run: 6462 64635. The kvm_run structure 6464======================== 6465 6466Application code obtains a pointer to the kvm_run structure by 6467mmap()ing a vcpu fd. From that point, application code can control 6468execution by changing fields in kvm_run prior to calling the KVM_RUN 6469ioctl, and obtain information about the reason KVM_RUN returned by 6470looking up structure members. 6471 6472:: 6473 6474 struct kvm_run { 6475 /* in */ 6476 __u8 request_interrupt_window; 6477 6478Request that KVM_RUN return when it becomes possible to inject external 6479interrupts into the guest. Useful in conjunction with KVM_INTERRUPT. 6480 6481:: 6482 6483 __u8 immediate_exit; 6484 6485This field is polled once when KVM_RUN starts; if non-zero, KVM_RUN 6486exits immediately, returning -EINTR. In the common scenario where a 6487signal is used to "kick" a VCPU out of KVM_RUN, this field can be used 6488to avoid usage of KVM_SET_SIGNAL_MASK, which has worse scalability. 6489Rather than blocking the signal outside KVM_RUN, userspace can set up 6490a signal handler that sets run->immediate_exit to a non-zero value. 6491 6492This field is ignored if KVM_CAP_IMMEDIATE_EXIT is not available. 6493 6494:: 6495 6496 __u8 padding1[6]; 6497 6498 /* out */ 6499 __u32 exit_reason; 6500 6501When KVM_RUN has returned successfully (return value 0), this informs 6502application code why KVM_RUN has returned. Allowable values for this 6503field are detailed below. 6504 6505:: 6506 6507 __u8 ready_for_interrupt_injection; 6508 6509If request_interrupt_window has been specified, this field indicates 6510an interrupt can be injected now with KVM_INTERRUPT. 6511 6512:: 6513 6514 __u8 if_flag; 6515 6516The value of the current interrupt flag. Only valid if in-kernel 6517local APIC is not used. 6518 6519:: 6520 6521 __u16 flags; 6522 6523More architecture-specific flags detailing state of the VCPU that may 6524affect the device's behavior. Current defined flags:: 6525 6526 /* x86, set if the VCPU is in system management mode */ 6527 #define KVM_RUN_X86_SMM (1 << 0) 6528 /* x86, set if bus lock detected in VM */ 6529 #define KVM_RUN_X86_BUS_LOCK (1 << 1) 6530 /* x86, set if the VCPU is executing a nested (L2) guest */ 6531 #define KVM_RUN_X86_GUEST_MODE (1 << 2) 6532 6533 /* arm64, set for KVM_EXIT_DEBUG */ 6534 #define KVM_DEBUG_ARCH_HSR_HIGH_VALID (1 << 0) 6535 6536:: 6537 6538 /* in (pre_kvm_run), out (post_kvm_run) */ 6539 __u64 cr8; 6540 6541The value of the cr8 register. Only valid if in-kernel local APIC is 6542not used. Both input and output. 6543 6544:: 6545 6546 __u64 apic_base; 6547 6548The value of the APIC BASE msr. Only valid if in-kernel local 6549APIC is not used. Both input and output. 6550 6551:: 6552 6553 union { 6554 /* KVM_EXIT_UNKNOWN */ 6555 struct { 6556 __u64 hardware_exit_reason; 6557 } hw; 6558 6559If exit_reason is KVM_EXIT_UNKNOWN, the vcpu has exited due to unknown 6560reasons. Further architecture-specific information is available in 6561hardware_exit_reason. 6562 6563:: 6564 6565 /* KVM_EXIT_FAIL_ENTRY */ 6566 struct { 6567 __u64 hardware_entry_failure_reason; 6568 __u32 cpu; /* if KVM_LAST_CPU */ 6569 } fail_entry; 6570 6571If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due 6572to unknown reasons. Further architecture-specific information is 6573available in hardware_entry_failure_reason. 6574 6575:: 6576 6577 /* KVM_EXIT_EXCEPTION */ 6578 struct { 6579 __u32 exception; 6580 __u32 error_code; 6581 } ex; 6582 6583Unused. 6584 6585:: 6586 6587 /* KVM_EXIT_IO */ 6588 struct { 6589 #define KVM_EXIT_IO_IN 0 6590 #define KVM_EXIT_IO_OUT 1 6591 __u8 direction; 6592 __u8 size; /* bytes */ 6593 __u16 port; 6594 __u32 count; 6595 __u64 data_offset; /* relative to kvm_run start */ 6596 } io; 6597 6598If exit_reason is KVM_EXIT_IO, then the vcpu has 6599executed a port I/O instruction which could not be satisfied by kvm. 6600data_offset describes where the data is located (KVM_EXIT_IO_OUT) or 6601where kvm expects application code to place the data for the next 6602KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array. 6603 6604:: 6605 6606 /* KVM_EXIT_DEBUG */ 6607 struct { 6608 struct kvm_debug_exit_arch arch; 6609 } debug; 6610 6611If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event 6612for which architecture specific information is returned. 6613 6614:: 6615 6616 /* KVM_EXIT_MMIO */ 6617 struct { 6618 __u64 phys_addr; 6619 __u8 data[8]; 6620 __u32 len; 6621 __u8 is_write; 6622 } mmio; 6623 6624If exit_reason is KVM_EXIT_MMIO, then the vcpu has 6625executed a memory-mapped I/O instruction which could not be satisfied 6626by kvm. The 'data' member contains the written data if 'is_write' is 6627true, and should be filled by application code otherwise. 6628 6629The 'data' member contains, in its first 'len' bytes, the value as it would 6630appear if the VCPU performed a load or store of the appropriate width directly 6631to the byte array. 6632 6633.. note:: 6634 6635 For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR, KVM_EXIT_XEN, 6636 KVM_EXIT_EPR, KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR the corresponding 6637 operations are complete (and guest state is consistent) only after userspace 6638 has re-entered the kernel with KVM_RUN. The kernel side will first finish 6639 incomplete operations and then check for pending signals. 6640 6641 The pending state of the operation is not preserved in state which is 6642 visible to userspace, thus userspace should ensure that the operation is 6643 completed before performing a live migration. Userspace can re-enter the 6644 guest with an unmasked signal pending or with the immediate_exit field set 6645 to complete pending operations without allowing any further instructions 6646 to be executed. 6647 6648:: 6649 6650 /* KVM_EXIT_HYPERCALL */ 6651 struct { 6652 __u64 nr; 6653 __u64 args[6]; 6654 __u64 ret; 6655 __u64 flags; 6656 } hypercall; 6657 6658 6659It is strongly recommended that userspace use ``KVM_EXIT_IO`` (x86) or 6660``KVM_EXIT_MMIO`` (all except s390) to implement functionality that 6661requires a guest to interact with host userspace. 6662 6663.. note:: KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO. 6664 6665For arm64: 6666---------- 6667 6668SMCCC exits can be enabled depending on the configuration of the SMCCC 6669filter. See the Documentation/virt/kvm/devices/vm.rst 6670``KVM_ARM_SMCCC_FILTER`` for more details. 6671 6672``nr`` contains the function ID of the guest's SMCCC call. Userspace is 6673expected to use the ``KVM_GET_ONE_REG`` ioctl to retrieve the call 6674parameters from the vCPU's GPRs. 6675 6676Definition of ``flags``: 6677 - ``KVM_HYPERCALL_EXIT_SMC``: Indicates that the guest used the SMC 6678 conduit to initiate the SMCCC call. If this bit is 0 then the guest 6679 used the HVC conduit for the SMCCC call. 6680 6681 - ``KVM_HYPERCALL_EXIT_16BIT``: Indicates that the guest used a 16bit 6682 instruction to initiate the SMCCC call. If this bit is 0 then the 6683 guest used a 32bit instruction. An AArch64 guest always has this 6684 bit set to 0. 6685 6686At the point of exit, PC points to the instruction immediately following 6687the trapping instruction. 6688 6689:: 6690 6691 /* KVM_EXIT_TPR_ACCESS */ 6692 struct { 6693 __u64 rip; 6694 __u32 is_write; 6695 __u32 pad; 6696 } tpr_access; 6697 6698To be documented (KVM_TPR_ACCESS_REPORTING). 6699 6700:: 6701 6702 /* KVM_EXIT_S390_SIEIC */ 6703 struct { 6704 __u8 icptcode; 6705 __u64 mask; /* psw upper half */ 6706 __u64 addr; /* psw lower half */ 6707 __u16 ipa; 6708 __u32 ipb; 6709 } s390_sieic; 6710 6711s390 specific. 6712 6713:: 6714 6715 /* KVM_EXIT_S390_RESET */ 6716 #define KVM_S390_RESET_POR 1 6717 #define KVM_S390_RESET_CLEAR 2 6718 #define KVM_S390_RESET_SUBSYSTEM 4 6719 #define KVM_S390_RESET_CPU_INIT 8 6720 #define KVM_S390_RESET_IPL 16 6721 __u64 s390_reset_flags; 6722 6723s390 specific. 6724 6725:: 6726 6727 /* KVM_EXIT_S390_UCONTROL */ 6728 struct { 6729 __u64 trans_exc_code; 6730 __u32 pgm_code; 6731 } s390_ucontrol; 6732 6733s390 specific. A page fault has occurred for a user controlled virtual 6734machine (KVM_VM_S390_UNCONTROL) on its host page table that cannot be 6735resolved by the kernel. 6736The program code and the translation exception code that were placed 6737in the cpu's lowcore are presented here as defined by the z Architecture 6738Principles of Operation Book in the Chapter for Dynamic Address Translation 6739(DAT) 6740 6741:: 6742 6743 /* KVM_EXIT_DCR */ 6744 struct { 6745 __u32 dcrn; 6746 __u32 data; 6747 __u8 is_write; 6748 } dcr; 6749 6750Deprecated - was used for 440 KVM. 6751 6752:: 6753 6754 /* KVM_EXIT_OSI */ 6755 struct { 6756 __u64 gprs[32]; 6757 } osi; 6758 6759MOL uses a special hypercall interface it calls 'OSI'. To enable it, we catch 6760hypercalls and exit with this exit struct that contains all the guest gprs. 6761 6762If exit_reason is KVM_EXIT_OSI, then the vcpu has triggered such a hypercall. 6763Userspace can now handle the hypercall and when it's done modify the gprs as 6764necessary. Upon guest entry all guest GPRs will then be replaced by the values 6765in this struct. 6766 6767:: 6768 6769 /* KVM_EXIT_PAPR_HCALL */ 6770 struct { 6771 __u64 nr; 6772 __u64 ret; 6773 __u64 args[9]; 6774 } papr_hcall; 6775 6776This is used on 64-bit PowerPC when emulating a pSeries partition, 6777e.g. with the 'pseries' machine type in qemu. It occurs when the 6778guest does a hypercall using the 'sc 1' instruction. The 'nr' field 6779contains the hypercall number (from the guest R3), and 'args' contains 6780the arguments (from the guest R4 - R12). Userspace should put the 6781return code in 'ret' and any extra returned values in args[]. 6782The possible hypercalls are defined in the Power Architecture Platform 6783Requirements (PAPR) document available from www.power.org (free 6784developer registration required to access it). 6785 6786:: 6787 6788 /* KVM_EXIT_S390_TSCH */ 6789 struct { 6790 __u16 subchannel_id; 6791 __u16 subchannel_nr; 6792 __u32 io_int_parm; 6793 __u32 io_int_word; 6794 __u32 ipb; 6795 __u8 dequeued; 6796 } s390_tsch; 6797 6798s390 specific. This exit occurs when KVM_CAP_S390_CSS_SUPPORT has been enabled 6799and TEST SUBCHANNEL was intercepted. If dequeued is set, a pending I/O 6800interrupt for the target subchannel has been dequeued and subchannel_id, 6801subchannel_nr, io_int_parm and io_int_word contain the parameters for that 6802interrupt. ipb is needed for instruction parameter decoding. 6803 6804:: 6805 6806 /* KVM_EXIT_EPR */ 6807 struct { 6808 __u32 epr; 6809 } epr; 6810 6811On FSL BookE PowerPC chips, the interrupt controller has a fast patch 6812interrupt acknowledge path to the core. When the core successfully 6813delivers an interrupt, it automatically populates the EPR register with 6814the interrupt vector number and acknowledges the interrupt inside 6815the interrupt controller. 6816 6817In case the interrupt controller lives in user space, we need to do 6818the interrupt acknowledge cycle through it to fetch the next to be 6819delivered interrupt vector using this exit. 6820 6821It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an 6822external interrupt has just been delivered into the guest. User space 6823should put the acknowledged interrupt vector into the 'epr' field. 6824 6825:: 6826 6827 /* KVM_EXIT_SYSTEM_EVENT */ 6828 struct { 6829 #define KVM_SYSTEM_EVENT_SHUTDOWN 1 6830 #define KVM_SYSTEM_EVENT_RESET 2 6831 #define KVM_SYSTEM_EVENT_CRASH 3 6832 #define KVM_SYSTEM_EVENT_WAKEUP 4 6833 #define KVM_SYSTEM_EVENT_SUSPEND 5 6834 #define KVM_SYSTEM_EVENT_SEV_TERM 6 6835 #define KVM_SYSTEM_EVENT_TDX_FATAL 7 6836 __u32 type; 6837 __u32 ndata; 6838 __u64 data[16]; 6839 } system_event; 6840 6841If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered 6842a system-level event using some architecture specific mechanism (hypercall 6843or some special instruction). In case of ARM64, this is triggered using 6844HVC instruction based PSCI call from the vcpu. 6845 6846The 'type' field describes the system-level event type. 6847Valid values for 'type' are: 6848 6849 - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the 6850 VM. Userspace is not obliged to honour this, and if it does honour 6851 this does not need to destroy the VM synchronously (ie it may call 6852 KVM_RUN again before shutdown finally occurs). 6853 - KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM. 6854 As with SHUTDOWN, userspace can choose to ignore the request, or 6855 to schedule the reset to occur in the future and may call KVM_RUN again. 6856 - KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest 6857 has requested a crash condition maintenance. Userspace can choose 6858 to ignore the request, or to gather VM memory core dump and/or 6859 reset/shutdown of the VM. 6860 - KVM_SYSTEM_EVENT_SEV_TERM -- an AMD SEV guest requested termination. 6861 The guest physical address of the guest's GHCB is stored in `data[0]`. 6862 - KVM_SYSTEM_EVENT_TDX_FATAL -- a TDX guest reported a fatal error state. 6863 KVM doesn't do any parsing or conversion, it just dumps 16 general-purpose 6864 registers to userspace, in ascending order of the 4-bit indices for x86-64 6865 general-purpose registers in instruction encoding, as defined in the Intel 6866 SDM. 6867 - KVM_SYSTEM_EVENT_WAKEUP -- the exiting vCPU is in a suspended state and 6868 KVM has recognized a wakeup event. Userspace may honor this event by 6869 marking the exiting vCPU as runnable, or deny it and call KVM_RUN again. 6870 - KVM_SYSTEM_EVENT_SUSPEND -- the guest has requested a suspension of 6871 the VM. 6872 6873If KVM_CAP_SYSTEM_EVENT_DATA is present, the 'data' field can contain 6874architecture specific information for the system-level event. Only 6875the first `ndata` items (possibly zero) of the data array are valid. 6876 6877 - for arm64, data[0] is set to KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 if 6878 the guest issued a SYSTEM_RESET2 call according to v1.1 of the PSCI 6879 specification. 6880 6881 - for arm64, data[0] is set to KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2 6882 if the guest issued a SYSTEM_OFF2 call according to v1.3 of the PSCI 6883 specification. 6884 6885 - for RISC-V, data[0] is set to the value of the second argument of the 6886 ``sbi_system_reset`` call. 6887 6888Previous versions of Linux defined a `flags` member in this struct. The 6889field is now aliased to `data[0]`. Userspace can assume that it is only 6890written if ndata is greater than 0. 6891 6892For arm/arm64: 6893-------------- 6894 6895KVM_SYSTEM_EVENT_SUSPEND exits are enabled with the 6896KVM_CAP_ARM_SYSTEM_SUSPEND VM capability. If a guest invokes the PSCI 6897SYSTEM_SUSPEND function, KVM will exit to userspace with this event 6898type. 6899 6900It is the sole responsibility of userspace to implement the PSCI 6901SYSTEM_SUSPEND call according to ARM DEN0022D.b 5.19 "SYSTEM_SUSPEND". 6902KVM does not change the vCPU's state before exiting to userspace, so 6903the call parameters are left in-place in the vCPU registers. 6904 6905Userspace is _required_ to take action for such an exit. It must 6906either: 6907 6908 - Honor the guest request to suspend the VM. Userspace can request 6909 in-kernel emulation of suspension by setting the calling vCPU's 6910 state to KVM_MP_STATE_SUSPENDED. Userspace must configure the vCPU's 6911 state according to the parameters passed to the PSCI function when 6912 the calling vCPU is resumed. See ARM DEN0022D.b 5.19.1 "Intended use" 6913 for details on the function parameters. 6914 6915 - Deny the guest request to suspend the VM. See ARM DEN0022D.b 5.19.2 6916 "Caller responsibilities" for possible return values. 6917 6918Hibernation using the PSCI SYSTEM_OFF2 call is enabled when PSCI v1.3 6919is enabled. If a guest invokes the PSCI SYSTEM_OFF2 function, KVM will 6920exit to userspace with the KVM_SYSTEM_EVENT_SHUTDOWN event type and with 6921data[0] set to KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2. The only 6922supported hibernate type for the SYSTEM_OFF2 function is HIBERNATE_OFF. 6923 6924:: 6925 6926 /* KVM_EXIT_IOAPIC_EOI */ 6927 struct { 6928 __u8 vector; 6929 } eoi; 6930 6931Indicates that the VCPU's in-kernel local APIC received an EOI for a 6932level-triggered IOAPIC interrupt. This exit only triggers when the 6933IOAPIC is implemented in userspace (i.e. KVM_CAP_SPLIT_IRQCHIP is enabled); 6934the userspace IOAPIC should process the EOI and retrigger the interrupt if 6935it is still asserted. Vector is the LAPIC interrupt vector for which the 6936EOI was received. 6937 6938:: 6939 6940 struct kvm_hyperv_exit { 6941 #define KVM_EXIT_HYPERV_SYNIC 1 6942 #define KVM_EXIT_HYPERV_HCALL 2 6943 #define KVM_EXIT_HYPERV_SYNDBG 3 6944 __u32 type; 6945 __u32 pad1; 6946 union { 6947 struct { 6948 __u32 msr; 6949 __u32 pad2; 6950 __u64 control; 6951 __u64 evt_page; 6952 __u64 msg_page; 6953 } synic; 6954 struct { 6955 __u64 input; 6956 __u64 result; 6957 __u64 params[2]; 6958 } hcall; 6959 struct { 6960 __u32 msr; 6961 __u32 pad2; 6962 __u64 control; 6963 __u64 status; 6964 __u64 send_page; 6965 __u64 recv_page; 6966 __u64 pending_page; 6967 } syndbg; 6968 } u; 6969 }; 6970 /* KVM_EXIT_HYPERV */ 6971 struct kvm_hyperv_exit hyperv; 6972 6973Indicates that the VCPU exits into userspace to process some tasks 6974related to Hyper-V emulation. 6975 6976Valid values for 'type' are: 6977 6978 - KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about 6979 6980Hyper-V SynIC state change. Notification is used to remap SynIC 6981event/message pages and to enable/disable SynIC messages/events processing 6982in userspace. 6983 6984 - KVM_EXIT_HYPERV_SYNDBG -- synchronously notify user-space about 6985 6986Hyper-V Synthetic debugger state change. Notification is used to either update 6987the pending_page location or to send a control command (send the buffer located 6988in send_page or recv a buffer to recv_page). 6989 6990:: 6991 6992 /* KVM_EXIT_ARM_NISV */ 6993 struct { 6994 __u64 esr_iss; 6995 __u64 fault_ipa; 6996 } arm_nisv; 6997 6998Used on arm64 systems. If a guest accesses memory not in a memslot, 6999KVM will typically return to userspace and ask it to do MMIO emulation on its 7000behalf. However, for certain classes of instructions, no instruction decode 7001(direction, length of memory access) is provided, and fetching and decoding 7002the instruction from the VM is overly complicated to live in the kernel. 7003 7004Historically, when this situation occurred, KVM would print a warning and kill 7005the VM. KVM assumed that if the guest accessed non-memslot memory, it was 7006trying to do I/O, which just couldn't be emulated, and the warning message was 7007phrased accordingly. However, what happened more often was that a guest bug 7008caused access outside the guest memory areas which should lead to a more 7009meaningful warning message and an external abort in the guest, if the access 7010did not fall within an I/O window. 7011 7012Userspace implementations can query for KVM_CAP_ARM_NISV_TO_USER, and enable 7013this capability at VM creation. Once this is done, these types of errors will 7014instead return to userspace with KVM_EXIT_ARM_NISV, with the valid bits from 7015the ESR_EL2 in the esr_iss field, and the faulting IPA in the fault_ipa field. 7016Userspace can either fix up the access if it's actually an I/O access by 7017decoding the instruction from guest memory (if it's very brave) and continue 7018executing the guest, or it can decide to suspend, dump, or restart the guest. 7019 7020Note that KVM does not skip the faulting instruction as it does for 7021KVM_EXIT_MMIO, but userspace has to emulate any change to the processing state 7022if it decides to decode and emulate the instruction. 7023 7024This feature isn't available to protected VMs, as userspace does not 7025have access to the state that is required to perform the emulation. 7026Instead, a data abort exception is directly injected in the guest. 7027Note that although KVM_CAP_ARM_NISV_TO_USER will be reported if 7028queried outside of a protected VM context, the feature will not be 7029exposed if queried on a protected VM file descriptor. 7030 7031:: 7032 7033 /* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */ 7034 struct { 7035 __u8 error; /* user -> kernel */ 7036 __u8 pad[7]; 7037 __u32 reason; /* kernel -> user */ 7038 __u32 index; /* kernel -> user */ 7039 __u64 data; /* kernel <-> user */ 7040 } msr; 7041 7042Used on x86 systems. When the VM capability KVM_CAP_X86_USER_SPACE_MSR is 7043enabled, MSR accesses to registers that would invoke a #GP by KVM kernel code 7044may instead trigger a KVM_EXIT_X86_RDMSR exit for reads and KVM_EXIT_X86_WRMSR 7045exit for writes. 7046 7047The "reason" field specifies why the MSR interception occurred. Userspace will 7048only receive MSR exits when a particular reason was requested during through 7049ENABLE_CAP. Currently valid exit reasons are: 7050 7051============================ ======================================== 7052 KVM_MSR_EXIT_REASON_UNKNOWN access to MSR that is unknown to KVM 7053 KVM_MSR_EXIT_REASON_INVAL access to invalid MSRs or reserved bits 7054 KVM_MSR_EXIT_REASON_FILTER access blocked by KVM_X86_SET_MSR_FILTER 7055============================ ======================================== 7056 7057For KVM_EXIT_X86_RDMSR, the "index" field tells userspace which MSR the guest 7058wants to read. To respond to this request with a successful read, userspace 7059writes the respective data into the "data" field and must continue guest 7060execution to ensure the read data is transferred into guest register state. 7061 7062If the RDMSR request was unsuccessful, userspace indicates that with a "1" in 7063the "error" field. This will inject a #GP into the guest when the VCPU is 7064executed again. 7065 7066For KVM_EXIT_X86_WRMSR, the "index" field tells userspace which MSR the guest 7067wants to write. Once finished processing the event, userspace must continue 7068vCPU execution. If the MSR write was unsuccessful, userspace also sets the 7069"error" field to "1". 7070 7071See KVM_X86_SET_MSR_FILTER for details on the interaction with MSR filtering. 7072 7073:: 7074 7075 7076 struct kvm_xen_exit { 7077 #define KVM_EXIT_XEN_HCALL 1 7078 __u32 type; 7079 union { 7080 struct { 7081 __u32 longmode; 7082 __u32 cpl; 7083 __u64 input; 7084 __u64 result; 7085 __u64 params[6]; 7086 } hcall; 7087 } u; 7088 }; 7089 /* KVM_EXIT_XEN */ 7090 struct kvm_hyperv_exit xen; 7091 7092Indicates that the VCPU exits into userspace to process some tasks 7093related to Xen emulation. 7094 7095Valid values for 'type' are: 7096 7097 - KVM_EXIT_XEN_HCALL -- synchronously notify user-space about Xen hypercall. 7098 Userspace is expected to place the hypercall result into the appropriate 7099 field before invoking KVM_RUN again. 7100 7101:: 7102 7103 /* KVM_EXIT_RISCV_SBI */ 7104 struct { 7105 unsigned long extension_id; 7106 unsigned long function_id; 7107 unsigned long args[6]; 7108 unsigned long ret[2]; 7109 } riscv_sbi; 7110 7111If exit reason is KVM_EXIT_RISCV_SBI then it indicates that the VCPU has 7112done a SBI call which is not handled by KVM RISC-V kernel module. The details 7113of the SBI call are available in 'riscv_sbi' member of kvm_run structure. The 7114'extension_id' field of 'riscv_sbi' represents SBI extension ID whereas the 7115'function_id' field represents function ID of given SBI extension. The 'args' 7116array field of 'riscv_sbi' represents parameters for the SBI call and 'ret' 7117array field represents return values. The userspace should update the return 7118values of SBI call before resuming the VCPU. For more details on RISC-V SBI 7119spec refer, https://github.com/riscv/riscv-sbi-doc. 7120 7121:: 7122 7123 /* KVM_EXIT_MEMORY_FAULT */ 7124 struct { 7125 #define KVM_MEMORY_EXIT_FLAG_PRIVATE (1ULL << 3) 7126 __u64 flags; 7127 __u64 gpa; 7128 __u64 size; 7129 } memory_fault; 7130 7131KVM_EXIT_MEMORY_FAULT indicates the vCPU has encountered a memory fault that 7132could not be resolved by KVM. The 'gpa' and 'size' (in bytes) describe the 7133guest physical address range [gpa, gpa + size) of the fault. The 'flags' field 7134describes properties of the faulting access that are likely pertinent: 7135 7136 - KVM_MEMORY_EXIT_FLAG_PRIVATE - When set, indicates the memory fault occurred 7137 on a private memory access. When clear, indicates the fault occurred on a 7138 shared access. 7139 7140Note! KVM_EXIT_MEMORY_FAULT is unique among all KVM exit reasons in that it 7141accompanies a return code of '-1', not '0'! errno will always be set to EFAULT 7142or EHWPOISON when KVM exits with KVM_EXIT_MEMORY_FAULT, userspace should assume 7143kvm_run.exit_reason is stale/undefined for all other error numbers. 7144 7145:: 7146 7147 /* KVM_EXIT_NOTIFY */ 7148 struct { 7149 #define KVM_NOTIFY_CONTEXT_INVALID (1 << 0) 7150 __u32 flags; 7151 } notify; 7152 7153Used on x86 systems. When the VM capability KVM_CAP_X86_NOTIFY_VMEXIT is 7154enabled, a VM exit generated if no event window occurs in VM non-root mode 7155for a specified amount of time. Once KVM_X86_NOTIFY_VMEXIT_USER is set when 7156enabling the cap, it would exit to userspace with the exit reason 7157KVM_EXIT_NOTIFY for further handling. The "flags" field contains more 7158detailed info. 7159 7160The valid value for 'flags' is: 7161 7162 - KVM_NOTIFY_CONTEXT_INVALID -- the VM context is corrupted and not valid 7163 in VMCS. It would run into unknown result if resume the target VM. 7164 7165:: 7166 7167 /* Fix the size of the union. */ 7168 char padding[256]; 7169 }; 7170 7171 /* 7172 * shared registers between kvm and userspace. 7173 * kvm_valid_regs specifies the register classes set by the host 7174 * kvm_dirty_regs specified the register classes dirtied by userspace 7175 * struct kvm_sync_regs is architecture specific, as well as the 7176 * bits for kvm_valid_regs and kvm_dirty_regs 7177 */ 7178 __u64 kvm_valid_regs; 7179 __u64 kvm_dirty_regs; 7180 union { 7181 struct kvm_sync_regs regs; 7182 char padding[SYNC_REGS_SIZE_BYTES]; 7183 } s; 7184 7185If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access 7186certain guest registers without having to call SET/GET_*REGS. Thus we can 7187avoid some system call overhead if userspace has to handle the exit. 7188Userspace can query the validity of the structure by checking 7189kvm_valid_regs for specific bits. These bits are architecture specific 7190and usually define the validity of a groups of registers. (e.g. one bit 7191for general purpose registers) 7192 7193Please note that the kernel is allowed to use the kvm_run structure as the 7194primary storage for certain register types. Therefore, the kernel may use the 7195values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set. 7196 7197 7198.. _cap_enable: 7199 72006. Capabilities that can be enabled on vCPUs 7201============================================ 7202 7203There are certain capabilities that change the behavior of the virtual CPU or 7204the virtual machine when enabled. To enable them, please see 7205:ref:`KVM_ENABLE_CAP`. 7206 7207Below you can find a list of capabilities and what their effect on the vCPU or 7208the virtual machine is when enabling them. 7209 7210The following information is provided along with the description: 7211 7212 Architectures: 7213 which instruction set architectures provide this ioctl. 7214 x86 includes both i386 and x86_64. 7215 7216 Target: 7217 whether this is a per-vcpu or per-vm capability. 7218 7219 Parameters: 7220 what parameters are accepted by the capability. 7221 7222 Returns: 7223 the return value. General error numbers (EBADF, ENOMEM, EINVAL) 7224 are not detailed, but errors with specific meanings are. 7225 7226 72276.1 KVM_CAP_PPC_OSI 7228------------------- 7229 7230:Architectures: ppc 7231:Target: vcpu 7232:Parameters: none 7233:Returns: 0 on success; -1 on error 7234 7235This capability enables interception of OSI hypercalls that otherwise would 7236be treated as normal system calls to be injected into the guest. OSI hypercalls 7237were invented by Mac-on-Linux to have a standardized communication mechanism 7238between the guest and the host. 7239 7240When this capability is enabled, KVM_EXIT_OSI can occur. 7241 7242 72436.2 KVM_CAP_PPC_PAPR 7244-------------------- 7245 7246:Architectures: ppc 7247:Target: vcpu 7248:Parameters: none 7249:Returns: 0 on success; -1 on error 7250 7251This capability enables interception of PAPR hypercalls. PAPR hypercalls are 7252done using the hypercall instruction "sc 1". 7253 7254It also sets the guest privilege level to "supervisor" mode. Usually the guest 7255runs in "hypervisor" privilege mode with a few missing features. 7256 7257In addition to the above, it changes the semantics of SDR1. In this mode, the 7258HTAB address part of SDR1 contains an HVA instead of a GPA, as PAPR keeps the 7259HTAB invisible to the guest. 7260 7261When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur. 7262 7263 72646.3 KVM_CAP_SW_TLB 7265------------------ 7266 7267:Architectures: ppc 7268:Target: vcpu 7269:Parameters: args[0] is the address of a struct kvm_config_tlb 7270:Returns: 0 on success; -1 on error 7271 7272:: 7273 7274 struct kvm_config_tlb { 7275 __u64 params; 7276 __u64 array; 7277 __u32 mmu_type; 7278 __u32 array_len; 7279 }; 7280 7281Configures the virtual CPU's TLB array, establishing a shared memory area 7282between userspace and KVM. The "params" and "array" fields are userspace 7283addresses of mmu-type-specific data structures. The "array_len" field is an 7284safety mechanism, and should be set to the size in bytes of the memory that 7285userspace has reserved for the array. It must be at least the size dictated 7286by "mmu_type" and "params". 7287 7288While KVM_RUN is active, the shared region is under control of KVM. Its 7289contents are undefined, and any modification by userspace results in 7290boundedly undefined behavior. 7291 7292On return from KVM_RUN, the shared region will reflect the current state of 7293the guest's TLB. If userspace makes any changes, it must call KVM_DIRTY_TLB 7294to tell KVM which entries have been changed, prior to calling KVM_RUN again 7295on this vcpu. 7296 7297For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV: 7298 7299 - The "params" field is of type "struct kvm_book3e_206_tlb_params". 7300 - The "array" field points to an array of type "struct 7301 kvm_book3e_206_tlb_entry". 7302 - The array consists of all entries in the first TLB, followed by all 7303 entries in the second TLB. 7304 - Within a TLB, entries are ordered first by increasing set number. Within a 7305 set, entries are ordered by way (increasing ESEL). 7306 - The hash for determining set number in TLB0 is: (MAS2 >> 12) & (num_sets - 1) 7307 where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value. 7308 - The tsize field of mas1 shall be set to 4K on TLB0, even though the 7309 hardware ignores this value for TLB0. 7310 73116.4 KVM_CAP_S390_CSS_SUPPORT 7312---------------------------- 7313 7314:Architectures: s390 7315:Target: vcpu 7316:Parameters: none 7317:Returns: 0 on success; -1 on error 7318 7319This capability enables support for handling of channel I/O instructions. 7320 7321TEST PENDING INTERRUPTION and the interrupt portion of TEST SUBCHANNEL are 7322handled in-kernel, while the other I/O instructions are passed to userspace. 7323 7324When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST 7325SUBCHANNEL intercepts. 7326 7327Note that even though this capability is enabled per-vcpu, the complete 7328virtual machine is affected. 7329 73306.5 KVM_CAP_PPC_EPR 7331------------------- 7332 7333:Architectures: ppc 7334:Target: vcpu 7335:Parameters: args[0] defines whether the proxy facility is active 7336:Returns: 0 on success; -1 on error 7337 7338This capability enables or disables the delivery of interrupts through the 7339external proxy facility. 7340 7341When enabled (args[0] != 0), every time the guest gets an external interrupt 7342delivered, it automatically exits into user space with a KVM_EXIT_EPR exit 7343to receive the topmost interrupt vector. 7344 7345When disabled (args[0] == 0), behavior is as if this facility is unsupported. 7346 7347When this capability is enabled, KVM_EXIT_EPR can occur. 7348 73496.6 KVM_CAP_IRQ_MPIC 7350-------------------- 7351 7352:Architectures: ppc 7353:Parameters: args[0] is the MPIC device fd; 7354 args[1] is the MPIC CPU number for this vcpu 7355 7356This capability connects the vcpu to an in-kernel MPIC device. 7357 73586.7 KVM_CAP_IRQ_XICS 7359-------------------- 7360 7361:Architectures: ppc 7362:Target: vcpu 7363:Parameters: args[0] is the XICS device fd; 7364 args[1] is the XICS CPU number (server ID) for this vcpu 7365 7366This capability connects the vcpu to an in-kernel XICS device. 7367 73686.8 KVM_CAP_S390_IRQCHIP 7369------------------------ 7370 7371:Architectures: s390 7372:Target: vm 7373:Parameters: none 7374 7375This capability enables the in-kernel irqchip for s390. Please refer to 7376"4.24 KVM_CREATE_IRQCHIP" for details. 7377 73786.9 KVM_CAP_MIPS_FPU 7379-------------------- 7380 7381:Architectures: mips 7382:Target: vcpu 7383:Parameters: args[0] is reserved for future use (should be 0). 7384 7385This capability allows the use of the host Floating Point Unit by the guest. It 7386allows the Config1.FP bit to be set to enable the FPU in the guest. Once this is 7387done the ``KVM_REG_MIPS_FPR_*`` and ``KVM_REG_MIPS_FCR_*`` registers can be 7388accessed (depending on the current guest FPU register mode), and the Status.FR, 7389Config5.FRE bits are accessible via the KVM API and also from the guest, 7390depending on them being supported by the FPU. 7391 73926.10 KVM_CAP_MIPS_MSA 7393--------------------- 7394 7395:Architectures: mips 7396:Target: vcpu 7397:Parameters: args[0] is reserved for future use (should be 0). 7398 7399This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest. 7400It allows the Config3.MSAP bit to be set to enable the use of MSA by the guest. 7401Once this is done the ``KVM_REG_MIPS_VEC_*`` and ``KVM_REG_MIPS_MSA_*`` 7402registers can be accessed, and the Config5.MSAEn bit is accessible via the 7403KVM API and also from the guest. 7404 74056.74 KVM_CAP_SYNC_REGS 7406---------------------- 7407 7408:Architectures: s390, x86 7409:Target: s390: always enabled, x86: vcpu 7410:Parameters: none 7411:Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register 7412 sets are supported 7413 (bitfields defined in arch/x86/include/uapi/asm/kvm.h). 7414 7415As described above in the kvm_sync_regs struct info in section :ref:`kvm_run`, 7416KVM_CAP_SYNC_REGS "allow[s] userspace to access certain guest registers 7417without having to call SET/GET_*REGS". This reduces overhead by eliminating 7418repeated ioctl calls for setting and/or getting register values. This is 7419particularly important when userspace is making synchronous guest state 7420modifications, e.g. when emulating and/or intercepting instructions in 7421userspace. 7422 7423For s390 specifics, please refer to the source code. 7424 7425For x86: 7426 7427- the register sets to be copied out to kvm_run are selectable 7428 by userspace (rather that all sets being copied out for every exit). 7429- vcpu_events are available in addition to regs and sregs. 7430 7431For x86, the 'kvm_valid_regs' field of struct kvm_run is overloaded to 7432function as an input bit-array field set by userspace to indicate the 7433specific register sets to be copied out on the next exit. 7434 7435To indicate when userspace has modified values that should be copied into 7436the vCPU, the all architecture bitarray field, 'kvm_dirty_regs' must be set. 7437This is done using the same bitflags as for the 'kvm_valid_regs' field. 7438If the dirty bit is not set, then the register set values will not be copied 7439into the vCPU even if they've been modified. 7440 7441Unused bitfields in the bitarrays must be set to zero. 7442 7443:: 7444 7445 struct kvm_sync_regs { 7446 struct kvm_regs regs; 7447 struct kvm_sregs sregs; 7448 struct kvm_vcpu_events events; 7449 }; 7450 74516.75 KVM_CAP_PPC_IRQ_XIVE 7452------------------------- 7453 7454:Architectures: ppc 7455:Target: vcpu 7456:Parameters: args[0] is the XIVE device fd; 7457 args[1] is the XIVE CPU number (server ID) for this vcpu 7458 7459This capability connects the vcpu to an in-kernel XIVE device. 7460 74616.76 KVM_CAP_HYPERV_SYNIC 7462------------------------- 7463 7464:Architectures: x86 7465:Target: vcpu 7466 7467This capability, if KVM_CHECK_EXTENSION indicates that it is 7468available, means that the kernel has an implementation of the 7469Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is 7470used to support Windows Hyper-V based guest paravirt drivers(VMBus). 7471 7472In order to use SynIC, it has to be activated by setting this 7473capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this 7474will disable the use of APIC hardware virtualization even if supported 7475by the CPU, as it's incompatible with SynIC auto-EOI behavior. 7476 74776.77 KVM_CAP_HYPERV_SYNIC2 7478-------------------------- 7479 7480:Architectures: x86 7481:Target: vcpu 7482 7483This capability enables a newer version of Hyper-V Synthetic interrupt 7484controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM 7485doesn't clear SynIC message and event flags pages when they are enabled by 7486writing to the respective MSRs. 7487 74886.78 KVM_CAP_HYPERV_DIRECT_TLBFLUSH 7489----------------------------------- 7490 7491:Architectures: x86 7492:Target: vcpu 7493 7494This capability indicates that KVM running on top of Hyper-V hypervisor 7495enables Direct TLB flush for its guests meaning that TLB flush 7496hypercalls are handled by Level 0 hypervisor (Hyper-V) bypassing KVM. 7497Due to the different ABI for hypercall parameters between Hyper-V and 7498KVM, enabling this capability effectively disables all hypercall 7499handling by KVM (as some KVM hypercall may be mistakenly treated as TLB 7500flush hypercalls by Hyper-V) so userspace should disable KVM identification 7501in CPUID and only exposes Hyper-V identification. In this case, guest 7502thinks it's running on Hyper-V and only use Hyper-V hypercalls. 7503 75046.79 KVM_CAP_HYPERV_ENFORCE_CPUID 7505--------------------------------- 7506 7507:Architectures: x86 7508:Target: vcpu 7509 7510When enabled, KVM will disable emulated Hyper-V features provided to the 7511guest according to the bits Hyper-V CPUID feature leaves. Otherwise, all 7512currently implemented Hyper-V features are provided unconditionally when 7513Hyper-V identification is set in the HYPERV_CPUID_INTERFACE (0x40000001) 7514leaf. 7515 75166.80 KVM_CAP_ENFORCE_PV_FEATURE_CPUID 7517------------------------------------- 7518 7519:Architectures: x86 7520:Target: vcpu 7521 7522When enabled, KVM will disable paravirtual features provided to the 7523guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf 7524(0x40000001). Otherwise, a guest may use the paravirtual features 7525regardless of what has actually been exposed through the CPUID leaf. 7526 7527.. _KVM_CAP_DIRTY_LOG_RING: 7528 7529 7530.. _cap_enable_vm: 7531 75327. Capabilities that can be enabled on VMs 7533========================================== 7534 7535There are certain capabilities that change the behavior of the virtual 7536machine when enabled. To enable them, please see section 7537:ref:`KVM_ENABLE_CAP`. Below you can find a list of capabilities and 7538what their effect on the VM is when enabling them. 7539 7540The following information is provided along with the description: 7541 7542 Architectures: 7543 which instruction set architectures provide this ioctl. 7544 x86 includes both i386 and x86_64. 7545 7546 Parameters: 7547 what parameters are accepted by the capability. 7548 7549 Returns: 7550 the return value. General error numbers (EBADF, ENOMEM, EINVAL) 7551 are not detailed, but errors with specific meanings are. 7552 7553 75547.1 KVM_CAP_PPC_ENABLE_HCALL 7555---------------------------- 7556 7557:Architectures: ppc 7558:Parameters: args[0] is the sPAPR hcall number; 7559 args[1] is 0 to disable, 1 to enable in-kernel handling 7560 7561This capability controls whether individual sPAPR hypercalls (hcalls) 7562get handled by the kernel or not. Enabling or disabling in-kernel 7563handling of an hcall is effective across the VM. On creation, an 7564initial set of hcalls are enabled for in-kernel handling, which 7565consists of those hcalls for which in-kernel handlers were implemented 7566before this capability was implemented. If disabled, the kernel will 7567not to attempt to handle the hcall, but will always exit to userspace 7568to handle it. Note that it may not make sense to enable some and 7569disable others of a group of related hcalls, but KVM does not prevent 7570userspace from doing that. 7571 7572If the hcall number specified is not one that has an in-kernel 7573implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL 7574error. 7575 75767.2 KVM_CAP_S390_USER_SIGP 7577-------------------------- 7578 7579:Architectures: s390 7580:Parameters: none 7581 7582This capability controls which SIGP orders will be handled completely in user 7583space. With this capability enabled, all fast orders will be handled completely 7584in the kernel: 7585 7586- SENSE 7587- SENSE RUNNING 7588- EXTERNAL CALL 7589- EMERGENCY SIGNAL 7590- CONDITIONAL EMERGENCY SIGNAL 7591 7592All other orders will be handled completely in user space. 7593 7594Only privileged operation exceptions will be checked for in the kernel (or even 7595in the hardware prior to interception). If this capability is not enabled, the 7596old way of handling SIGP orders is used (partially in kernel and user space). 7597 75987.3 KVM_CAP_S390_VECTOR_REGISTERS 7599--------------------------------- 7600 7601:Architectures: s390 7602:Parameters: none 7603:Returns: 0 on success, negative value on error 7604 7605Allows use of the vector registers introduced with z13 processor, and 7606provides for the synchronization between host and user space. Will 7607return -EINVAL if the machine does not support vectors. 7608 76097.4 KVM_CAP_S390_USER_STSI 7610-------------------------- 7611 7612:Architectures: s390 7613:Parameters: none 7614 7615This capability allows post-handlers for the STSI instruction. After 7616initial handling in the kernel, KVM exits to user space with 7617KVM_EXIT_S390_STSI to allow user space to insert further data. 7618 7619Before exiting to userspace, kvm handlers should fill in s390_stsi field of 7620vcpu->run:: 7621 7622 struct { 7623 __u64 addr; 7624 __u8 ar; 7625 __u8 reserved; 7626 __u8 fc; 7627 __u8 sel1; 7628 __u16 sel2; 7629 } s390_stsi; 7630 7631 @addr - guest address of STSI SYSIB 7632 @fc - function code 7633 @sel1 - selector 1 7634 @sel2 - selector 2 7635 @ar - access register number 7636 7637KVM handlers should exit to userspace with rc = -EREMOTE. 7638 76397.5 KVM_CAP_SPLIT_IRQCHIP 7640------------------------- 7641 7642:Architectures: x86 7643:Parameters: args[0] - number of routes reserved for userspace IOAPICs 7644:Returns: 0 on success, -1 on error 7645 7646Create a local apic for each processor in the kernel. This can be used 7647instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the 7648IOAPIC and PIC (and also the PIT, even though this has to be enabled 7649separately). 7650 7651This capability also enables in kernel routing of interrupt requests; 7652when KVM_CAP_SPLIT_IRQCHIP only routes of KVM_IRQ_ROUTING_MSI type are 7653used in the IRQ routing table. The first args[0] MSI routes are reserved 7654for the IOAPIC pins. Whenever the LAPIC receives an EOI for these routes, 7655a KVM_EXIT_IOAPIC_EOI vmexit will be reported to userspace. 7656 7657Fails if VCPU has already been created, or if the irqchip is already in the 7658kernel (i.e. KVM_CREATE_IRQCHIP has already been called). 7659 76607.6 KVM_CAP_S390_RI 7661------------------- 7662 7663:Architectures: s390 7664:Parameters: none 7665 7666Allows use of runtime-instrumentation introduced with zEC12 processor. 7667Will return -EINVAL if the machine does not support runtime-instrumentation. 7668Will return -EBUSY if a VCPU has already been created. 7669 76707.7 KVM_CAP_X2APIC_API 7671---------------------- 7672 7673:Architectures: x86 7674:Parameters: args[0] - features that should be enabled 7675:Returns: 0 on success, -EINVAL when args[0] contains invalid features 7676 7677Valid feature flags in args[0] are:: 7678 7679 #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) 7680 #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) 7681 7682Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of 7683KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC, 7684allowing the use of 32-bit APIC IDs. See KVM_CAP_X2APIC_API in their 7685respective sections. 7686 7687KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK must be enabled for x2APIC to work 7688in logical mode or with more than 255 VCPUs. Otherwise, KVM treats 0xff 7689as a broadcast even in x2APIC mode in order to support physical x2APIC 7690without interrupt remapping. This is undesirable in logical mode, 7691where 0xff represents CPUs 0-7 in cluster 0. 7692 76937.8 KVM_CAP_S390_USER_INSTR0 7694---------------------------- 7695 7696:Architectures: s390 7697:Parameters: none 7698 7699With this capability enabled, all illegal instructions 0x0000 (2 bytes) will 7700be intercepted and forwarded to user space. User space can use this 7701mechanism e.g. to realize 2-byte software breakpoints. The kernel will 7702not inject an operating exception for these instructions, user space has 7703to take care of that. 7704 7705This capability can be enabled dynamically even if VCPUs were already 7706created and are running. 7707 77087.9 KVM_CAP_S390_GS 7709------------------- 7710 7711:Architectures: s390 7712:Parameters: none 7713:Returns: 0 on success; -EINVAL if the machine does not support 7714 guarded storage; -EBUSY if a VCPU has already been created. 7715 7716Allows use of guarded storage for the KVM guest. 7717 77187.10 KVM_CAP_S390_AIS 7719--------------------- 7720 7721:Architectures: s390 7722:Parameters: none 7723 7724Allow use of adapter-interruption suppression. 7725:Returns: 0 on success; -EBUSY if a VCPU has already been created. 7726 77277.11 KVM_CAP_PPC_SMT 7728-------------------- 7729 7730:Architectures: ppc 7731:Parameters: vsmt_mode, flags 7732 7733Enabling this capability on a VM provides userspace with a way to set 7734the desired virtual SMT mode (i.e. the number of virtual CPUs per 7735virtual core). The virtual SMT mode, vsmt_mode, must be a power of 2 7736between 1 and 8. On POWER8, vsmt_mode must also be no greater than 7737the number of threads per subcore for the host. Currently flags must 7738be 0. A successful call to enable this capability will result in 7739vsmt_mode being returned when the KVM_CAP_PPC_SMT capability is 7740subsequently queried for the VM. This capability is only supported by 7741HV KVM, and can only be set before any VCPUs have been created. 7742The KVM_CAP_PPC_SMT_POSSIBLE capability indicates which virtual SMT 7743modes are available. 7744 77457.12 KVM_CAP_PPC_FWNMI 7746---------------------- 7747 7748:Architectures: ppc 7749:Parameters: none 7750 7751With this capability a machine check exception in the guest address 7752space will cause KVM to exit the guest with NMI exit reason. This 7753enables QEMU to build error log and branch to guest kernel registered 7754machine check handling routine. Without this capability KVM will 7755branch to guests' 0x200 interrupt vector. 7756 77577.13 KVM_CAP_X86_DISABLE_EXITS 7758------------------------------ 7759 7760:Architectures: x86 7761:Parameters: args[0] defines which exits are disabled 7762:Returns: 0 on success, -EINVAL when args[0] contains invalid exits 7763 or if any vCPUs have already been created 7764 7765Valid bits in args[0] are:: 7766 7767 #define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) 7768 #define KVM_X86_DISABLE_EXITS_HLT (1 << 1) 7769 #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) 7770 #define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) 7771 7772Enabling this capability on a VM provides userspace with a way to no 7773longer intercept some instructions for improved latency in some 7774workloads, and is suggested when vCPUs are associated to dedicated 7775physical CPUs. More bits can be added in the future; userspace can 7776just pass the KVM_CHECK_EXTENSION result to KVM_ENABLE_CAP to disable 7777all such vmexits. 7778 7779Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits. 7780 77817.14 KVM_CAP_S390_HPAGE_1M 7782-------------------------- 7783 7784:Architectures: s390 7785:Parameters: none 7786:Returns: 0 on success, -EINVAL if hpage module parameter was not set 7787 or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL 7788 flag set 7789 7790With this capability the KVM support for memory backing with 1m pages 7791through hugetlbfs can be enabled for a VM. After the capability is 7792enabled, cmma can't be enabled anymore and pfmfi and the storage key 7793interpretation are disabled. If cmma has already been enabled or the 7794hpage module parameter is not set to 1, -EINVAL is returned. 7795 7796While it is generally possible to create a huge page backed VM without 7797this capability, the VM will not be able to run. 7798 77997.15 KVM_CAP_MSR_PLATFORM_INFO 7800------------------------------ 7801 7802:Architectures: x86 7803:Parameters: args[0] whether feature should be enabled or not 7804 7805With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise, 7806a #GP would be raised when the guest tries to access. Currently, this 7807capability does not enable write permissions of this MSR for the guest. 7808 78097.16 KVM_CAP_PPC_NESTED_HV 7810-------------------------- 7811 7812:Architectures: ppc 7813:Parameters: none 7814:Returns: 0 on success, -EINVAL when the implementation doesn't support 7815 nested-HV virtualization. 7816 7817HV-KVM on POWER9 and later systems allows for "nested-HV" 7818virtualization, which provides a way for a guest VM to run guests that 7819can run using the CPU's supervisor mode (privileged non-hypervisor 7820state). Enabling this capability on a VM depends on the CPU having 7821the necessary functionality and on the facility being enabled with a 7822kvm-hv module parameter. 7823 78247.17 KVM_CAP_EXCEPTION_PAYLOAD 7825------------------------------ 7826 7827:Architectures: x86 7828:Parameters: args[0] whether feature should be enabled or not 7829 7830With this capability enabled, CR2 will not be modified prior to the 7831emulated VM-exit when L1 intercepts a #PF exception that occurs in 7832L2. Similarly, for kvm-intel only, DR6 will not be modified prior to 7833the emulated VM-exit when L1 intercepts a #DB exception that occurs in 7834L2. As a result, when KVM_GET_VCPU_EVENTS reports a pending #PF (or 7835#DB) exception for L2, exception.has_payload will be set and the 7836faulting address (or the new DR6 bits*) will be reported in the 7837exception_payload field. Similarly, when userspace injects a #PF (or 7838#DB) into L2 using KVM_SET_VCPU_EVENTS, it is expected to set 7839exception.has_payload and to put the faulting address - or the new DR6 7840bits\ [#]_ - in the exception_payload field. 7841 7842This capability also enables exception.pending in struct 7843kvm_vcpu_events, which allows userspace to distinguish between pending 7844and injected exceptions. 7845 7846 7847.. [#] For the new DR6 bits, note that bit 16 is set iff the #DB exception 7848 will clear DR6.RTM. 7849 78507.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 7851-------------------------------------- 7852 7853:Architectures: x86, arm64, mips 7854:Parameters: args[0] whether feature should be enabled or not 7855 7856Valid flags are:: 7857 7858 #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) 7859 #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) 7860 7861With KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE is set, KVM_GET_DIRTY_LOG will not 7862automatically clear and write-protect all pages that are returned as dirty. 7863Rather, userspace will have to do this operation separately using 7864KVM_CLEAR_DIRTY_LOG. 7865 7866At the cost of a slightly more complicated operation, this provides better 7867scalability and responsiveness for two reasons. First, 7868KVM_CLEAR_DIRTY_LOG ioctl can operate on a 64-page granularity rather 7869than requiring to sync a full memslot; this ensures that KVM does not 7870take spinlocks for an extended period of time. Second, in some cases a 7871large amount of time can pass between a call to KVM_GET_DIRTY_LOG and 7872userspace actually using the data in the page. Pages can be modified 7873during this time, which is inefficient for both the guest and userspace: 7874the guest will incur a higher penalty due to write protection faults, 7875while userspace can see false reports of dirty pages. Manual reprotection 7876helps reducing this time, improving guest performance and reducing the 7877number of dirty log false positives. 7878 7879With KVM_DIRTY_LOG_INITIALLY_SET set, all the bits of the dirty bitmap 7880will be initialized to 1 when created. This also improves performance because 7881dirty logging can be enabled gradually in small chunks on the first call 7882to KVM_CLEAR_DIRTY_LOG. KVM_DIRTY_LOG_INITIALLY_SET depends on 7883KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (it is also only available on 7884x86 and arm64 for now). 7885 7886KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 was previously available under the name 7887KVM_CAP_MANUAL_DIRTY_LOG_PROTECT, but the implementation had bugs that make 7888it hard or impossible to use it correctly. The availability of 7889KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 signals that those bugs are fixed. 7890Userspace should not try to use KVM_CAP_MANUAL_DIRTY_LOG_PROTECT. 7891 78927.19 KVM_CAP_PPC_SECURE_GUEST 7893------------------------------ 7894 7895:Architectures: ppc 7896 7897This capability indicates that KVM is running on a host that has 7898ultravisor firmware and thus can support a secure guest. On such a 7899system, a guest can ask the ultravisor to make it a secure guest, 7900one whose memory is inaccessible to the host except for pages which 7901are explicitly requested to be shared with the host. The ultravisor 7902notifies KVM when a guest requests to become a secure guest, and KVM 7903has the opportunity to veto the transition. 7904 7905If present, this capability can be enabled for a VM, meaning that KVM 7906will allow the transition to secure guest mode. Otherwise KVM will 7907veto the transition. 7908 79097.20 KVM_CAP_HALT_POLL 7910---------------------- 7911 7912:Architectures: all 7913:Target: VM 7914:Parameters: args[0] is the maximum poll time in nanoseconds 7915:Returns: 0 on success; -1 on error 7916 7917KVM_CAP_HALT_POLL overrides the kvm.halt_poll_ns module parameter to set the 7918maximum halt-polling time for all vCPUs in the target VM. This capability can 7919be invoked at any time and any number of times to dynamically change the 7920maximum halt-polling time. 7921 7922See Documentation/virt/kvm/halt-polling.rst for more information on halt 7923polling. 7924 79257.21 KVM_CAP_X86_USER_SPACE_MSR 7926------------------------------- 7927 7928:Architectures: x86 7929:Target: VM 7930:Parameters: args[0] contains the mask of KVM_MSR_EXIT_REASON_* events to report 7931:Returns: 0 on success; -1 on error 7932 7933This capability allows userspace to intercept RDMSR and WRMSR instructions if 7934access to an MSR is denied. By default, KVM injects #GP on denied accesses. 7935 7936When a guest requests to read or write an MSR, KVM may not implement all MSRs 7937that are relevant to a respective system. It also does not differentiate by 7938CPU type. 7939 7940To allow more fine grained control over MSR handling, userspace may enable 7941this capability. With it enabled, MSR accesses that match the mask specified in 7942args[0] and would trigger a #GP inside the guest will instead trigger 7943KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications. Userspace 7944can then implement model specific MSR handling and/or user notifications 7945to inform a user that an MSR was not emulated/virtualized by KVM. 7946 7947The valid mask flags are: 7948 7949============================ =============================================== 7950 KVM_MSR_EXIT_REASON_UNKNOWN intercept accesses to unknown (to KVM) MSRs 7951 KVM_MSR_EXIT_REASON_INVAL intercept accesses that are architecturally 7952 invalid according to the vCPU model and/or mode 7953 KVM_MSR_EXIT_REASON_FILTER intercept accesses that are denied by userspace 7954 via KVM_X86_SET_MSR_FILTER 7955============================ =============================================== 7956 79577.22 KVM_CAP_X86_BUS_LOCK_EXIT 7958------------------------------- 7959 7960:Architectures: x86 7961:Target: VM 7962:Parameters: args[0] defines the policy used when bus locks detected in guest 7963:Returns: 0 on success, -EINVAL when args[0] contains invalid bits 7964 7965Valid bits in args[0] are:: 7966 7967 #define KVM_BUS_LOCK_DETECTION_OFF (1 << 0) 7968 #define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1) 7969 7970Enabling this capability on a VM provides userspace with a way to select a 7971policy to handle the bus locks detected in guest. Userspace can obtain the 7972supported modes from the result of KVM_CHECK_EXTENSION and define it through 7973the KVM_ENABLE_CAP. The supported modes are mutually-exclusive. 7974 7975This capability allows userspace to force VM exits on bus locks detected in the 7976guest, irrespective whether or not the host has enabled split-lock detection 7977(which triggers an #AC exception that KVM intercepts). This capability is 7978intended to mitigate attacks where a malicious/buggy guest can exploit bus 7979locks to degrade the performance of the whole system. 7980 7981If KVM_BUS_LOCK_DETECTION_OFF is set, KVM doesn't force guest bus locks to VM 7982exit, although the host kernel's split-lock #AC detection still applies, if 7983enabled. 7984 7985If KVM_BUS_LOCK_DETECTION_EXIT is set, KVM enables a CPU feature that ensures 7986bus locks in the guest trigger a VM exit, and KVM exits to userspace for all 7987such VM exits, e.g. to allow userspace to throttle the offending guest and/or 7988apply some other policy-based mitigation. When exiting to userspace, KVM sets 7989KVM_RUN_X86_BUS_LOCK in vcpu-run->flags, and conditionally sets the exit_reason 7990to KVM_EXIT_X86_BUS_LOCK. 7991 7992Note! Detected bus locks may be coincident with other exits to userspace, i.e. 7993KVM_RUN_X86_BUS_LOCK should be checked regardless of the primary exit reason if 7994userspace wants to take action on all detected bus locks. 7995 79967.23 KVM_CAP_PPC_DAWR1 7997---------------------- 7998 7999:Architectures: ppc 8000:Parameters: none 8001:Returns: 0 on success, -EINVAL when CPU doesn't support 2nd DAWR 8002 8003This capability can be used to check / enable 2nd DAWR feature provided 8004by POWER10 processor. 8005 8006 80077.24 KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 8008------------------------------------- 8009 8010:Architectures: x86 SEV enabled 8011:Type: vm 8012:Parameters: args[0] is the fd of the source vm 8013:Returns: 0 on success; ENOTTY on error 8014 8015This capability enables userspace to copy encryption context from the vm 8016indicated by the fd to the vm this is called on. 8017 8018This is intended to support in-guest workloads scheduled by the host. This 8019allows the in-guest workload to maintain its own NPTs and keeps the two vms 8020from accidentally clobbering each other with interrupts and the like (separate 8021APIC/MSRs/etc). 8022 80237.25 KVM_CAP_SGX_ATTRIBUTE 8024-------------------------- 8025 8026:Architectures: x86 8027:Target: VM 8028:Parameters: args[0] is a file handle of a SGX attribute file in securityfs 8029:Returns: 0 on success, -EINVAL if the file handle is invalid or if a requested 8030 attribute is not supported by KVM. 8031 8032KVM_CAP_SGX_ATTRIBUTE enables a userspace VMM to grant a VM access to one or 8033more privileged enclave attributes. args[0] must hold a file handle to a valid 8034SGX attribute file corresponding to an attribute that is supported/restricted 8035by KVM (currently only PROVISIONKEY). 8036 8037The SGX subsystem restricts access to a subset of enclave attributes to provide 8038additional security for an uncompromised kernel, e.g. use of the PROVISIONKEY 8039is restricted to deter malware from using the PROVISIONKEY to obtain a stable 8040system fingerprint. To prevent userspace from circumventing such restrictions 8041by running an enclave in a VM, KVM prevents access to privileged attributes by 8042default. 8043 8044See Documentation/arch/x86/sgx.rst for more details. 8045 80467.27 KVM_CAP_EXIT_ON_EMULATION_FAILURE 8047-------------------------------------- 8048 8049:Architectures: x86 8050:Parameters: args[0] whether the feature should be enabled or not 8051 8052When this capability is enabled, an emulation failure will result in an exit 8053to userspace with KVM_INTERNAL_ERROR (except when the emulator was invoked 8054to handle a VMware backdoor instruction). Furthermore, KVM will now provide up 8055to 15 instruction bytes for any exit to userspace resulting from an emulation 8056failure. When these exits to userspace occur use the emulation_failure struct 8057instead of the internal struct. They both have the same layout, but the 8058emulation_failure struct matches the content better. It also explicitly 8059defines the 'flags' field which is used to describe the fields in the struct 8060that are valid (ie: if KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES is 8061set in the 'flags' field then both 'insn_size' and 'insn_bytes' have valid data 8062in them.) 8063 80647.28 KVM_CAP_ARM_MTE 8065-------------------- 8066 8067:Architectures: arm64 8068:Parameters: none 8069 8070This capability indicates that KVM (and the hardware) supports exposing the 8071Memory Tagging Extensions (MTE) to the guest. It must also be enabled by the 8072VMM before creating any VCPUs to allow the guest access. Note that MTE is only 8073available to a guest running in AArch64 mode and enabling this capability will 8074cause attempts to create AArch32 VCPUs to fail. 8075 8076When enabled the guest is able to access tags associated with any memory given 8077to the guest. KVM will ensure that the tags are maintained during swap or 8078hibernation of the host; however the VMM needs to manually save/restore the 8079tags as appropriate if the VM is migrated. 8080 8081When this capability is enabled all memory in memslots must be mapped as 8082``MAP_ANONYMOUS`` or with a RAM-based file mapping (``tmpfs``, ``memfd``), 8083attempts to create a memslot with an invalid mmap will result in an 8084-EINVAL return. 8085 8086When enabled the VMM may make use of the ``KVM_ARM_MTE_COPY_TAGS`` ioctl to 8087perform a bulk copy of tags to/from the guest. 8088 80897.29 KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 8090------------------------------------- 8091 8092:Architectures: x86 SEV enabled 8093:Type: vm 8094:Parameters: args[0] is the fd of the source vm 8095:Returns: 0 on success 8096 8097This capability enables userspace to migrate the encryption context from the VM 8098indicated by the fd to the VM this is called on. 8099 8100This is intended to support intra-host migration of VMs between userspace VMMs, 8101upgrading the VMM process without interrupting the guest. 8102 81037.31 KVM_CAP_DISABLE_QUIRKS2 8104---------------------------- 8105 8106:Parameters: args[0] - set of KVM quirks to disable 8107:Architectures: x86 8108:Type: vm 8109 8110This capability, if enabled, will cause KVM to disable some behavior 8111quirks. 8112 8113Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of 8114quirks that can be disabled in KVM. 8115 8116The argument to KVM_ENABLE_CAP for this capability is a bitmask of 8117quirks to disable, and must be a subset of the bitmask returned by 8118KVM_CHECK_EXTENSION. 8119 8120The valid bits in cap.args[0] are: 8121 8122=================================== ============================================ 8123 KVM_X86_QUIRK_LINT0_REENABLED By default, the reset value for the LVT 8124 LINT0 register is 0x700 (APIC_MODE_EXTINT). 8125 When this quirk is disabled, the reset value 8126 is 0x10000 (APIC_LVT_MASKED). 8127 8128 KVM_X86_QUIRK_CD_NW_CLEARED By default, KVM clears CR0.CD and CR0.NW on 8129 AMD CPUs to workaround buggy guest firmware 8130 that runs in perpetuity with CR0.CD, i.e. 8131 with caches in "no fill" mode. 8132 8133 When this quirk is disabled, KVM does not 8134 change the value of CR0.CD and CR0.NW. 8135 8136 KVM_X86_QUIRK_LAPIC_MMIO_HOLE By default, the MMIO LAPIC interface is 8137 available even when configured for x2APIC 8138 mode. When this quirk is disabled, KVM 8139 disables the MMIO LAPIC interface if the 8140 LAPIC is in x2APIC mode. 8141 8142 KVM_X86_QUIRK_OUT_7E_INC_RIP By default, KVM pre-increments %rip before 8143 exiting to userspace for an OUT instruction 8144 to port 0x7e. When this quirk is disabled, 8145 KVM does not pre-increment %rip before 8146 exiting to userspace. 8147 8148 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT When this quirk is disabled, KVM sets 8149 CPUID.01H:ECX[bit 3] (MONITOR/MWAIT) if 8150 IA32_MISC_ENABLE[bit 18] (MWAIT) is set. 8151 Additionally, when this quirk is disabled, 8152 KVM clears CPUID.01H:ECX[bit 3] if 8153 IA32_MISC_ENABLE[bit 18] is cleared. 8154 8155 KVM_X86_QUIRK_FIX_HYPERCALL_INSN By default, KVM rewrites guest 8156 VMMCALL/VMCALL instructions to match the 8157 vendor's hypercall instruction for the 8158 system. When this quirk is disabled, KVM 8159 will no longer rewrite invalid guest 8160 hypercall instructions. Executing the 8161 incorrect hypercall instruction will 8162 generate a #UD within the guest. 8163 8164KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if 8165 they are intercepted) as NOPs regardless of 8166 whether or not MONITOR/MWAIT are supported 8167 according to guest CPUID. When this quirk 8168 is disabled and KVM_X86_DISABLE_EXITS_MWAIT 8169 is not set (MONITOR/MWAIT are intercepted), 8170 KVM will inject a #UD on MONITOR/MWAIT if 8171 they're unsupported per guest CPUID. Note, 8172 KVM will modify MONITOR/MWAIT support in 8173 guest CPUID on writes to MISC_ENABLE if 8174 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is 8175 disabled. 8176 8177KVM_X86_QUIRK_SLOT_ZAP_ALL By default, for KVM_X86_DEFAULT_VM VMs, KVM 8178 invalidates all SPTEs in all memslots and 8179 address spaces when a memslot is deleted or 8180 moved. When this quirk is disabled (or the 8181 VM type isn't KVM_X86_DEFAULT_VM), KVM only 8182 ensures the backing memory of the deleted 8183 or moved memslot isn't reachable, i.e KVM 8184 _may_ invalidate only SPTEs related to the 8185 memslot. 8186 8187KVM_X86_QUIRK_STUFF_FEATURE_MSRS By default, at vCPU creation, KVM sets the 8188 vCPU's MSR_IA32_PERF_CAPABILITIES (0x345), 8189 MSR_IA32_ARCH_CAPABILITIES (0x10a), 8190 MSR_PLATFORM_INFO (0xce), and all VMX MSRs 8191 (0x480..0x492) to the maximal capabilities 8192 supported by KVM. KVM also sets 8193 MSR_IA32_UCODE_REV (0x8b) to an arbitrary 8194 value (which is different for Intel vs. 8195 AMD). Lastly, when guest CPUID is set (by 8196 userspace), KVM modifies select VMX MSR 8197 fields to force consistency between guest 8198 CPUID and L2's effective ISA. When this 8199 quirk is disabled, KVM zeroes the vCPU's MSR 8200 values (with two exceptions, see below), 8201 i.e. treats the feature MSRs like CPUID 8202 leaves and gives userspace full control of 8203 the vCPU model definition. This quirk does 8204 not affect VMX MSRs CR0/CR4_FIXED1 (0x487 8205 and 0x489), as KVM does now allow them to 8206 be set by userspace (KVM sets them based on 8207 guest CPUID, for safety purposes). 8208 8209KVM_X86_QUIRK_IGNORE_GUEST_PAT By default, on Intel platforms, KVM ignores 8210 guest PAT and forces the effective memory 8211 type to WB in EPT. The quirk is not available 8212 on Intel platforms which are incapable of 8213 safely honoring guest PAT (i.e., without CPU 8214 self-snoop, KVM always ignores guest PAT and 8215 forces effective memory type to WB). It is 8216 also ignored on AMD platforms or, on Intel, 8217 when a VM has non-coherent DMA devices 8218 assigned; KVM always honors guest PAT in 8219 such case. The quirk is needed to avoid 8220 slowdowns on certain Intel Xeon platforms 8221 (e.g. ICX, SPR) where self-snoop feature is 8222 supported but UC is slow enough to cause 8223 issues with some older guests that use 8224 UC instead of WC to map the video RAM. 8225 Userspace can disable the quirk to honor 8226 guest PAT if it knows that there is no such 8227 guest software, for example if it does not 8228 expose a bochs graphics device (which is 8229 known to have had a buggy driver). 8230=================================== ============================================ 8231 82327.32 KVM_CAP_MAX_VCPU_ID 8233------------------------ 8234 8235:Architectures: x86 8236:Target: VM 8237:Parameters: args[0] - maximum APIC ID value set for current VM 8238:Returns: 0 on success, -EINVAL if args[0] is beyond KVM_MAX_VCPU_IDS 8239 supported in KVM or if it has been set. 8240 8241This capability allows userspace to specify maximum possible APIC ID 8242assigned for current VM session prior to the creation of vCPUs, saving 8243memory for data structures indexed by the APIC ID. Userspace is able 8244to calculate the limit to APIC ID values from designated 8245CPU topology. 8246 8247The value can be changed only until KVM_ENABLE_CAP is set to a nonzero 8248value or until a vCPU is created. Upon creation of the first vCPU, 8249if the value was set to zero or KVM_ENABLE_CAP was not invoked, KVM 8250uses the return value of KVM_CHECK_EXTENSION(KVM_CAP_MAX_VCPU_ID) as 8251the maximum APIC ID. 8252 82537.33 KVM_CAP_X86_NOTIFY_VMEXIT 8254------------------------------ 8255 8256:Architectures: x86 8257:Target: VM 8258:Parameters: args[0] is the value of notify window as well as some flags 8259:Returns: 0 on success, -EINVAL if args[0] contains invalid flags or notify 8260 VM exit is unsupported. 8261 8262Bits 63:32 of args[0] are used for notify window. 8263Bits 31:0 of args[0] are for some flags. Valid bits are:: 8264 8265 #define KVM_X86_NOTIFY_VMEXIT_ENABLED (1 << 0) 8266 #define KVM_X86_NOTIFY_VMEXIT_USER (1 << 1) 8267 8268This capability allows userspace to configure the notify VM exit on/off 8269in per-VM scope during VM creation. Notify VM exit is disabled by default. 8270When userspace sets KVM_X86_NOTIFY_VMEXIT_ENABLED bit in args[0], VMM will 8271enable this feature with the notify window provided, which will generate 8272a VM exit if no event window occurs in VM non-root mode for a specified of 8273time (notify window). 8274 8275If KVM_X86_NOTIFY_VMEXIT_USER is set in args[0], upon notify VM exits happen, 8276KVM would exit to userspace for handling. 8277 8278This capability is aimed to mitigate the threat that malicious VMs can 8279cause CPU stuck (due to event windows don't open up) and make the CPU 8280unavailable to host or other VMs. 8281 82827.35 KVM_CAP_X86_APIC_BUS_CYCLES_NS 8283----------------------------------- 8284 8285:Architectures: x86 8286:Target: VM 8287:Parameters: args[0] is the desired APIC bus clock rate, in nanoseconds 8288:Returns: 0 on success, -EINVAL if args[0] contains an invalid value for the 8289 frequency or if any vCPUs have been created, -ENXIO if a virtual 8290 local APIC has not been created using KVM_CREATE_IRQCHIP. 8291 8292This capability sets the VM's APIC bus clock frequency, used by KVM's in-kernel 8293virtual APIC when emulating APIC timers. KVM's default value can be retrieved 8294by KVM_CHECK_EXTENSION. 8295 8296Note: Userspace is responsible for correctly configuring CPUID 0x15, a.k.a. the 8297core crystal clock frequency, if a non-zero CPUID 0x15 is exposed to the guest. 8298 82997.36 KVM_CAP_DIRTY_LOG_RING/KVM_CAP_DIRTY_LOG_RING_ACQ_REL 8300---------------------------------------------------------- 8301 8302:Architectures: x86, arm64 8303:Type: vm 8304:Parameters: args[0] - size of the dirty log ring 8305 8306KVM is capable of tracking dirty memory using ring buffers that are 8307mmapped into userspace; there is one dirty ring per vcpu. 8308 8309The dirty ring is available to userspace as an array of 8310``struct kvm_dirty_gfn``. Each dirty entry is defined as:: 8311 8312 struct kvm_dirty_gfn { 8313 __u32 flags; 8314 __u32 slot; /* as_id | slot_id */ 8315 __u64 offset; 8316 }; 8317 8318The following values are defined for the flags field to define the 8319current state of the entry:: 8320 8321 #define KVM_DIRTY_GFN_F_DIRTY BIT(0) 8322 #define KVM_DIRTY_GFN_F_RESET BIT(1) 8323 #define KVM_DIRTY_GFN_F_MASK 0x3 8324 8325Userspace should call KVM_ENABLE_CAP ioctl right after KVM_CREATE_VM 8326ioctl to enable this capability for the new guest and set the size of 8327the rings. Enabling the capability is only allowed before creating any 8328vCPU, and the size of the ring must be a power of two. The larger the 8329ring buffer, the less likely the ring is full and the VM is forced to 8330exit to userspace. The optimal size depends on the workload, but it is 8331recommended that it be at least 64 KiB (4096 entries). 8332 8333Just like for dirty page bitmaps, the buffer tracks writes to 8334all user memory regions for which the KVM_MEM_LOG_DIRTY_PAGES flag was 8335set in KVM_SET_USER_MEMORY_REGION. Once a memory region is registered 8336with the flag set, userspace can start harvesting dirty pages from the 8337ring buffer. 8338 8339An entry in the ring buffer can be unused (flag bits ``00``), 8340dirty (flag bits ``01``) or harvested (flag bits ``1X``). The 8341state machine for the entry is as follows:: 8342 8343 dirtied harvested reset 8344 00 -----------> 01 -------------> 1X -------+ 8345 ^ | 8346 | | 8347 +------------------------------------------+ 8348 8349To harvest the dirty pages, userspace accesses the mmapped ring buffer 8350to read the dirty GFNs. If the flags has the DIRTY bit set (at this stage 8351the RESET bit must be cleared), then it means this GFN is a dirty GFN. 8352The userspace should harvest this GFN and mark the flags from state 8353``01b`` to ``1Xb`` (bit 0 will be ignored by KVM, but bit 1 must be set 8354to show that this GFN is harvested and waiting for a reset), and move 8355on to the next GFN. The userspace should continue to do this until the 8356flags of a GFN have the DIRTY bit cleared, meaning that it has harvested 8357all the dirty GFNs that were available. 8358 8359Note that on weakly ordered architectures, userspace accesses to the 8360ring buffer (and more specifically the 'flags' field) must be ordered, 8361using load-acquire/store-release accessors when available, or any 8362other memory barrier that will ensure this ordering. 8363 8364It's not necessary for userspace to harvest the all dirty GFNs at once. 8365However it must collect the dirty GFNs in sequence, i.e., the userspace 8366program cannot skip one dirty GFN to collect the one next to it. 8367 8368After processing one or more entries in the ring buffer, userspace 8369calls the VM ioctl KVM_RESET_DIRTY_RINGS to notify the kernel about 8370it, so that the kernel will reprotect those collected GFNs. 8371Therefore, the ioctl must be called *before* reading the content of 8372the dirty pages. 8373 8374The dirty ring can get full. When it happens, the KVM_RUN of the 8375vcpu will return with exit reason KVM_EXIT_DIRTY_LOG_FULL. 8376 8377The dirty ring interface has a major difference comparing to the 8378KVM_GET_DIRTY_LOG interface in that, when reading the dirty ring from 8379userspace, it's still possible that the kernel has not yet flushed the 8380processor's dirty page buffers into the kernel buffer (with dirty bitmaps, the 8381flushing is done by the KVM_GET_DIRTY_LOG ioctl). To achieve that, one 8382needs to kick the vcpu out of KVM_RUN using a signal. The resulting 8383vmexit ensures that all dirty GFNs are flushed to the dirty rings. 8384 8385NOTE: KVM_CAP_DIRTY_LOG_RING_ACQ_REL is the only capability that 8386should be exposed by weakly ordered architecture, in order to indicate 8387the additional memory ordering requirements imposed on userspace when 8388reading the state of an entry and mutating it from DIRTY to HARVESTED. 8389Architecture with TSO-like ordering (such as x86) are allowed to 8390expose both KVM_CAP_DIRTY_LOG_RING and KVM_CAP_DIRTY_LOG_RING_ACQ_REL 8391to userspace. 8392 8393After enabling the dirty rings, the userspace needs to detect the 8394capability of KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP to see whether the 8395ring structures can be backed by per-slot bitmaps. With this capability 8396advertised, it means the architecture can dirty guest pages without 8397vcpu/ring context, so that some of the dirty information will still be 8398maintained in the bitmap structure. KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 8399can't be enabled if the capability of KVM_CAP_DIRTY_LOG_RING_ACQ_REL 8400hasn't been enabled, or any memslot has been existing. 8401 8402Note that the bitmap here is only a backup of the ring structure. The 8403use of the ring and bitmap combination is only beneficial if there is 8404only a very small amount of memory that is dirtied out of vcpu/ring 8405context. Otherwise, the stand-alone per-slot bitmap mechanism needs to 8406be considered. 8407 8408To collect dirty bits in the backup bitmap, userspace can use the same 8409KVM_GET_DIRTY_LOG ioctl. KVM_CLEAR_DIRTY_LOG isn't needed as long as all 8410the generation of the dirty bits is done in a single pass. Collecting 8411the dirty bitmap should be the very last thing that the VMM does before 8412considering the state as complete. VMM needs to ensure that the dirty 8413state is final and avoid missing dirty pages from another ioctl ordered 8414after the bitmap collection. 8415 8416NOTE: Multiple examples of using the backup bitmap: (1) save vgic/its 8417tables through command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} on 8418KVM device "kvm-arm-vgic-its". (2) restore vgic/its tables through 8419command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_RESTORE_TABLES} on KVM device 8420"kvm-arm-vgic-its". VGICv3 LPI pending status is restored. (3) save 8421vgic3 pending table through KVM_DEV_ARM_VGIC_{GRP_CTRL, SAVE_PENDING_TABLES} 8422command on KVM device "kvm-arm-vgic-v3". 8423 84247.37 KVM_CAP_PMU_CAPABILITY 8425--------------------------- 8426 8427:Architectures: x86 8428:Type: vm 8429:Parameters: arg[0] is bitmask of PMU virtualization capabilities. 8430:Returns: 0 on success, -EINVAL when arg[0] contains invalid bits 8431 8432This capability alters PMU virtualization in KVM. 8433 8434Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of 8435PMU virtualization capabilities that can be adjusted on a VM. 8436 8437The argument to KVM_ENABLE_CAP is also a bitmask and selects specific 8438PMU virtualization capabilities to be applied to the VM. This can 8439only be invoked on a VM prior to the creation of VCPUs. 8440 8441At this time, KVM_PMU_CAP_DISABLE is the only capability. Setting 8442this capability will disable PMU virtualization for that VM. Usermode 8443should adjust CPUID leaf 0xA to reflect that the PMU is disabled. 8444 84457.38 KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 8446------------------------------------- 8447 8448:Architectures: x86 8449:Type: vm 8450:Parameters: arg[0] must be 0. 8451:Returns: 0 on success, -EPERM if the userspace process does not 8452 have CAP_SYS_BOOT, -EINVAL if args[0] is not 0 or any vCPUs have been 8453 created. 8454 8455This capability disables the NX huge pages mitigation for iTLB MULTIHIT. 8456 8457The capability has no effect if the nx_huge_pages module parameter is not set. 8458 8459This capability may only be set before any vCPUs are created. 8460 84617.39 KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 8462--------------------------------------- 8463 8464:Architectures: arm64 8465:Type: vm 8466:Parameters: arg[0] is the new split chunk size. 8467:Returns: 0 on success, -EINVAL if any memslot was already created. 8468 8469This capability sets the chunk size used in Eager Page Splitting. 8470 8471Eager Page Splitting improves the performance of dirty-logging (used 8472in live migrations) when guest memory is backed by huge-pages. It 8473avoids splitting huge-pages (into PAGE_SIZE pages) on fault, by doing 8474it eagerly when enabling dirty logging (with the 8475KVM_MEM_LOG_DIRTY_PAGES flag for a memory region), or when using 8476KVM_CLEAR_DIRTY_LOG. 8477 8478The chunk size specifies how many pages to break at a time, using a 8479single allocation for each chunk. Bigger the chunk size, more pages 8480need to be allocated ahead of time. 8481 8482The chunk size needs to be a valid block size. The list of acceptable 8483block sizes is exposed in KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES as a 848464-bit bitmap (each bit describing a block size). The default value is 84850, to disable the eager page splitting. 8486 84877.40 KVM_CAP_EXIT_HYPERCALL 8488--------------------------- 8489 8490:Architectures: x86 8491:Type: vm 8492 8493This capability, if enabled, will cause KVM to exit to userspace 8494with KVM_EXIT_HYPERCALL exit reason to process some hypercalls. 8495 8496Calling KVM_CHECK_EXTENSION for this capability will return a bitmask 8497of hypercalls that can be configured to exit to userspace. 8498Right now, the only such hypercall is KVM_HC_MAP_GPA_RANGE. 8499 8500The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset 8501of the result of KVM_CHECK_EXTENSION. KVM will forward to userspace 8502the hypercalls whose corresponding bit is in the argument, and return 8503ENOSYS for the others. 8504 85057.41 KVM_CAP_ARM_SYSTEM_SUSPEND 8506------------------------------- 8507 8508:Architectures: arm64 8509:Type: vm 8510 8511When enabled, KVM will exit to userspace with KVM_EXIT_SYSTEM_EVENT of 8512type KVM_SYSTEM_EVENT_SUSPEND to process the guest suspend request. 8513 85147.37 KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 8515------------------------------------- 8516 8517:Architectures: arm64 8518:Target: VM 8519:Parameters: None 8520:Returns: 0 on success, -EINVAL if vCPUs have been created before enabling this 8521 capability. 8522 8523This capability changes the behavior of the registers that identify a PE 8524implementation of the Arm architecture: MIDR_EL1, REVIDR_EL1, and AIDR_EL1. 8525By default, these registers are visible to userspace but treated as invariant. 8526 8527When this capability is enabled, KVM allows userspace to change the 8528aforementioned registers before the first KVM_RUN. These registers are VM 8529scoped, meaning that the same set of values are presented on all vCPUs in a 8530given VM. 8531 85328. Other capabilities. 8533====================== 8534 8535This section lists capabilities that give information about other 8536features of the KVM implementation. 8537 85388.1 KVM_CAP_PPC_HWRNG 8539--------------------- 8540 8541:Architectures: ppc 8542 8543This capability, if KVM_CHECK_EXTENSION indicates that it is 8544available, means that the kernel has an implementation of the 8545H_RANDOM hypercall backed by a hardware random-number generator. 8546If present, the kernel H_RANDOM handler can be enabled for guest use 8547with the KVM_CAP_PPC_ENABLE_HCALL capability. 8548 85498.3 KVM_CAP_PPC_MMU_RADIX 8550------------------------- 8551 8552:Architectures: ppc 8553 8554This capability, if KVM_CHECK_EXTENSION indicates that it is 8555available, means that the kernel can support guests using the 8556radix MMU defined in Power ISA V3.00 (as implemented in the POWER9 8557processor). 8558 85598.4 KVM_CAP_PPC_MMU_HASH_V3 8560--------------------------- 8561 8562:Architectures: ppc 8563 8564This capability, if KVM_CHECK_EXTENSION indicates that it is 8565available, means that the kernel can support guests using the 8566hashed page table MMU defined in Power ISA V3.00 (as implemented in 8567the POWER9 processor), including in-memory segment tables. 8568 85698.5 KVM_CAP_MIPS_VZ 8570------------------- 8571 8572:Architectures: mips 8573 8574This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that 8575it is available, means that full hardware assisted virtualization capabilities 8576of the hardware are available for use through KVM. An appropriate 8577KVM_VM_MIPS_* type must be passed to KVM_CREATE_VM to create a VM which 8578utilises it. 8579 8580If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is 8581available, it means that the VM is using full hardware assisted virtualization 8582capabilities of the hardware. This is useful to check after creating a VM with 8583KVM_VM_MIPS_DEFAULT. 8584 8585The value returned by KVM_CHECK_EXTENSION should be compared against known 8586values (see below). All other values are reserved. This is to allow for the 8587possibility of other hardware assisted virtualization implementations which 8588may be incompatible with the MIPS VZ ASE. 8589 8590== ========================================================================== 8591 0 The trap & emulate implementation is in use to run guest code in user 8592 mode. Guest virtual memory segments are rearranged to fit the guest in the 8593 user mode address space. 8594 8595 1 The MIPS VZ ASE is in use, providing full hardware assisted 8596 virtualization, including standard guest virtual memory segments. 8597== ========================================================================== 8598 85998.7 KVM_CAP_MIPS_64BIT 8600---------------------- 8601 8602:Architectures: mips 8603 8604This capability indicates the supported architecture type of the guest, i.e. the 8605supported register and address width. 8606 8607The values returned when this capability is checked by KVM_CHECK_EXTENSION on a 8608kvm VM handle correspond roughly to the CP0_Config.AT register field, and should 8609be checked specifically against known values (see below). All other values are 8610reserved. 8611 8612== ======================================================================== 8613 0 MIPS32 or microMIPS32. 8614 Both registers and addresses are 32-bits wide. 8615 It will only be possible to run 32-bit guest code. 8616 8617 1 MIPS64 or microMIPS64 with access only to 32-bit compatibility segments. 8618 Registers are 64-bits wide, but addresses are 32-bits wide. 8619 64-bit guest code may run but cannot access MIPS64 memory segments. 8620 It will also be possible to run 32-bit guest code. 8621 8622 2 MIPS64 or microMIPS64 with access to all address segments. 8623 Both registers and addresses are 64-bits wide. 8624 It will be possible to run 64-bit or 32-bit guest code. 8625== ======================================================================== 8626 86278.9 KVM_CAP_ARM_USER_IRQ 8628------------------------ 8629 8630:Architectures: arm64 8631 8632This capability, if KVM_CHECK_EXTENSION indicates that it is available, means 8633that if userspace creates a VM without an in-kernel interrupt controller, it 8634will be notified of changes to the output level of in-kernel emulated devices, 8635which can generate virtual interrupts, presented to the VM. 8636For such VMs, on every return to userspace, the kernel 8637updates the vcpu's run->s.regs.device_irq_level field to represent the actual 8638output level of the device. 8639 8640Whenever kvm detects a change in the device output level, kvm guarantees at 8641least one return to userspace before running the VM. This exit could either 8642be a KVM_EXIT_INTR or any other exit event, like KVM_EXIT_MMIO. This way, 8643userspace can always sample the device output level and re-compute the state of 8644the userspace interrupt controller. Userspace should always check the state 8645of run->s.regs.device_irq_level on every kvm exit. 8646The value in run->s.regs.device_irq_level can represent both level and edge 8647triggered interrupt signals, depending on the device. Edge triggered interrupt 8648signals will exit to userspace with the bit in run->s.regs.device_irq_level 8649set exactly once per edge signal. 8650 8651The field run->s.regs.device_irq_level is available independent of 8652run->kvm_valid_regs or run->kvm_dirty_regs bits. 8653 8654If KVM_CAP_ARM_USER_IRQ is supported, the KVM_CHECK_EXTENSION ioctl returns a 8655number larger than 0 indicating the version of this capability is implemented 8656and thereby which bits in run->s.regs.device_irq_level can signal values. 8657 8658Currently the following bits are defined for the device_irq_level bitmap:: 8659 8660 KVM_CAP_ARM_USER_IRQ >= 1: 8661 8662 KVM_ARM_DEV_EL1_VTIMER - EL1 virtual timer 8663 KVM_ARM_DEV_EL1_PTIMER - EL1 physical timer 8664 KVM_ARM_DEV_PMU - ARM PMU overflow interrupt signal 8665 8666Future versions of kvm may implement additional events. These will get 8667indicated by returning a higher number from KVM_CHECK_EXTENSION and will be 8668listed above. 8669 86708.10 KVM_CAP_PPC_SMT_POSSIBLE 8671----------------------------- 8672 8673:Architectures: ppc 8674 8675Querying this capability returns a bitmap indicating the possible 8676virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N 8677(counting from the right) is set, then a virtual SMT mode of 2^N is 8678available. 8679 86808.12 KVM_CAP_HYPERV_VP_INDEX 8681---------------------------- 8682 8683:Architectures: x86 8684 8685This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its 8686value is used to denote the target vcpu for a SynIC interrupt. For 8687compatibility, KVM initializes this msr to KVM's internal vcpu index. When this 8688capability is absent, userspace can still query this msr's value. 8689 86908.13 KVM_CAP_S390_AIS_MIGRATION 8691------------------------------- 8692 8693:Architectures: s390 8694 8695This capability indicates if the flic device will be able to get/set the 8696AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows 8697to discover this without having to create a flic device. 8698 86998.14 KVM_CAP_S390_PSW 8700--------------------- 8701 8702:Architectures: s390 8703 8704This capability indicates that the PSW is exposed via the kvm_run structure. 8705 87068.15 KVM_CAP_S390_GMAP 8707---------------------- 8708 8709:Architectures: s390 8710 8711This capability indicates that the user space memory used as guest mapping can 8712be anywhere in the user memory address space, as long as the memory slots are 8713aligned and sized to a segment (1MB) boundary. 8714 87158.16 KVM_CAP_S390_COW 8716--------------------- 8717 8718:Architectures: s390 8719 8720This capability indicates that the user space memory used as guest mapping can 8721use copy-on-write semantics as well as dirty pages tracking via read-only page 8722tables. 8723 87248.17 KVM_CAP_S390_BPB 8725--------------------- 8726 8727:Architectures: s390 8728 8729This capability indicates that kvm will implement the interfaces to handle 8730reset, migration and nested KVM for branch prediction blocking. The stfle 8731facility 82 should not be provided to the guest without this capability. 8732 87338.18 KVM_CAP_HYPERV_TLBFLUSH 8734---------------------------- 8735 8736:Architectures: x86 8737 8738This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush 8739hypercalls: 8740HvFlushVirtualAddressSpace, HvFlushVirtualAddressSpaceEx, 8741HvFlushVirtualAddressList, HvFlushVirtualAddressListEx. 8742 87438.19 KVM_CAP_ARM_INJECT_SERROR_ESR 8744---------------------------------- 8745 8746:Architectures: arm64 8747 8748This capability indicates that userspace can specify (via the 8749KVM_SET_VCPU_EVENTS ioctl) the syndrome value reported to the guest when it 8750takes a virtual SError interrupt exception. 8751If KVM advertises this capability, userspace can only specify the ISS field for 8752the ESR syndrome. Other parts of the ESR, such as the EC are generated by the 8753CPU when the exception is taken. If this virtual SError is taken to EL1 using 8754AArch64, this value will be reported in the ISS field of ESR_ELx. 8755 8756See KVM_CAP_VCPU_EVENTS for more details. 8757 87588.20 KVM_CAP_HYPERV_SEND_IPI 8759---------------------------- 8760 8761:Architectures: x86 8762 8763This capability indicates that KVM supports paravirtualized Hyper-V IPI send 8764hypercalls: 8765HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx. 8766 87678.22 KVM_CAP_S390_VCPU_RESETS 8768----------------------------- 8769 8770:Architectures: s390 8771 8772This capability indicates that the KVM_S390_NORMAL_RESET and 8773KVM_S390_CLEAR_RESET ioctls are available. 8774 87758.23 KVM_CAP_S390_PROTECTED 8776--------------------------- 8777 8778:Architectures: s390 8779 8780This capability indicates that the Ultravisor has been initialized and 8781KVM can therefore start protected VMs. 8782This capability governs the KVM_S390_PV_COMMAND ioctl and the 8783KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected 8784guests when the state change is invalid. 8785 87868.24 KVM_CAP_STEAL_TIME 8787----------------------- 8788 8789:Architectures: arm64, x86 8790 8791This capability indicates that KVM supports steal time accounting. 8792When steal time accounting is supported it may be enabled with 8793architecture-specific interfaces. This capability and the architecture- 8794specific interfaces must be consistent, i.e. if one says the feature 8795is supported, than the other should as well and vice versa. For arm64 8796see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL". 8797For x86 see Documentation/virt/kvm/x86/msr.rst "MSR_KVM_STEAL_TIME". 8798 87998.25 KVM_CAP_S390_DIAG318 8800------------------------- 8801 8802:Architectures: s390 8803 8804This capability enables a guest to set information about its control program 8805(i.e. guest kernel type and version). The information is helpful during 8806system/firmware service events, providing additional data about the guest 8807environments running on the machine. 8808 8809The information is associated with the DIAGNOSE 0x318 instruction, which sets 8810an 8-byte value consisting of a one-byte Control Program Name Code (CPNC) and 8811a 7-byte Control Program Version Code (CPVC). The CPNC determines what 8812environment the control program is running in (e.g. Linux, z/VM...), and the 8813CPVC is used for information specific to OS (e.g. Linux version, Linux 8814distribution...) 8815 8816If this capability is available, then the CPNC and CPVC can be synchronized 8817between KVM and userspace via the sync regs mechanism (KVM_SYNC_DIAG318). 8818 88198.26 KVM_CAP_X86_USER_SPACE_MSR 8820------------------------------- 8821 8822:Architectures: x86 8823 8824This capability indicates that KVM supports deflection of MSR reads and 8825writes to user space. It can be enabled on a VM level. If enabled, MSR 8826accesses that would usually trigger a #GP by KVM into the guest will 8827instead get bounced to user space through the KVM_EXIT_X86_RDMSR and 8828KVM_EXIT_X86_WRMSR exit notifications. 8829 88308.27 KVM_CAP_X86_MSR_FILTER 8831--------------------------- 8832 8833:Architectures: x86 8834 8835This capability indicates that KVM supports that accesses to user defined MSRs 8836may be rejected. With this capability exposed, KVM exports new VM ioctl 8837KVM_X86_SET_MSR_FILTER which user space can call to specify bitmaps of MSR 8838ranges that KVM should deny access to. 8839 8840In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to 8841trap and emulate MSRs that are outside of the scope of KVM as well as 8842limit the attack surface on KVM's MSR emulation code. 8843 88448.30 KVM_CAP_XEN_HVM 8845-------------------- 8846 8847:Architectures: x86 8848 8849This capability indicates the features that Xen supports for hosting Xen 8850PVHVM guests. Valid flags are:: 8851 8852 #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) 8853 #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) 8854 #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) 8855 #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) 8856 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) 8857 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) 8858 #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) 8859 #define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) 8860 8861The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG 8862ioctl is available, for the guest to set its hypercall page. 8863 8864If KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL is also set, the same flag may also be 8865provided in the flags to KVM_XEN_HVM_CONFIG, without providing hypercall page 8866contents, to request that KVM generate hypercall page content automatically 8867and also enable interception of guest hypercalls with KVM_EXIT_XEN. 8868 8869The KVM_XEN_HVM_CONFIG_SHARED_INFO flag indicates the availability of the 8870KVM_XEN_HVM_SET_ATTR, KVM_XEN_HVM_GET_ATTR, KVM_XEN_VCPU_SET_ATTR and 8871KVM_XEN_VCPU_GET_ATTR ioctls, as well as the delivery of exception vectors 8872for event channel upcalls when the evtchn_upcall_pending field of a vcpu's 8873vcpu_info is set. 8874 8875The KVM_XEN_HVM_CONFIG_RUNSTATE flag indicates that the runstate-related 8876features KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR/_CURRENT/_DATA/_ADJUST are 8877supported by the KVM_XEN_VCPU_SET_ATTR/KVM_XEN_VCPU_GET_ATTR ioctls. 8878 8879The KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL flag indicates that IRQ routing entries 8880of the type KVM_IRQ_ROUTING_XEN_EVTCHN are supported, with the priority 8881field set to indicate 2 level event channel delivery. 8882 8883The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indicates that KVM supports 8884injecting event channel events directly into the guest with the 8885KVM_XEN_HVM_EVTCHN_SEND ioctl. It also indicates support for the 8886KVM_XEN_ATTR_TYPE_EVTCHN/XEN_VERSION HVM attributes and the 8887KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID/TIMER/UPCALL_VECTOR vCPU attributes. 8888related to event channel delivery, timers, and the XENVER_version 8889interception. 8890 8891The KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG flag indicates that KVM supports 8892the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute in the KVM_XEN_SET_ATTR 8893and KVM_XEN_GET_ATTR ioctls. This controls whether KVM will set the 8894XEN_RUNSTATE_UPDATE flag in guest memory mapped vcpu_runstate_info during 8895updates of the runstate information. Note that versions of KVM which support 8896the RUNSTATE feature above, but not the RUNSTATE_UPDATE_FLAG feature, will 8897always set the XEN_RUNSTATE_UPDATE flag when updating the guest structure, 8898which is perhaps counterintuitive. When this flag is advertised, KVM will 8899behave more correctly, not using the XEN_RUNSTATE_UPDATE flag until/unless 8900specifically enabled (by the guest making the hypercall, causing the VMM 8901to enable the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute). 8902 8903The KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag indicates that KVM supports 8904clearing the PVCLOCK_TSC_STABLE_BIT flag in Xen pvclock sources. This will be 8905done when the KVM_CAP_XEN_HVM ioctl sets the 8906KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag. 8907 89088.31 KVM_CAP_SPAPR_MULTITCE 8909--------------------------- 8910 8911:Architectures: ppc 8912:Type: vm 8913 8914This capability means the kernel is capable of handling hypercalls 8915H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user 8916space. This significantly accelerates DMA operations for PPC KVM guests. 8917User space should expect that its handlers for these hypercalls 8918are not going to be called if user space previously registered LIOBN 8919in KVM (via KVM_CREATE_SPAPR_TCE or similar calls). 8920 8921In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest, 8922user space might have to advertise it for the guest. For example, 8923IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is 8924present in the "ibm,hypertas-functions" device-tree property. 8925 8926The hypercalls mentioned above may or may not be processed successfully 8927in the kernel based fast path. If they can not be handled by the kernel, 8928they will get passed on to user space. So user space still has to have 8929an implementation for these despite the in kernel acceleration. 8930 8931This capability is always enabled. 8932 89338.32 KVM_CAP_PTP_KVM 8934-------------------- 8935 8936:Architectures: arm64 8937 8938This capability indicates that the KVM virtual PTP service is 8939supported in the host. A VMM can check whether the service is 8940available to the guest on migration. 8941 89428.37 KVM_CAP_S390_PROTECTED_DUMP 8943-------------------------------- 8944 8945:Architectures: s390 8946:Type: vm 8947 8948This capability indicates that KVM and the Ultravisor support dumping 8949PV guests. The `KVM_PV_DUMP` command is available for the 8950`KVM_S390_PV_COMMAND` ioctl and the `KVM_PV_INFO` command provides 8951dump related UV data. Also the vcpu ioctl `KVM_S390_PV_CPU_COMMAND` is 8952available and supports the `KVM_PV_DUMP_CPU` subcommand. 8953 89548.39 KVM_CAP_S390_CPU_TOPOLOGY 8955------------------------------ 8956 8957:Architectures: s390 8958:Type: vm 8959 8960This capability indicates that KVM will provide the S390 CPU Topology 8961facility which consist of the interpretation of the PTF instruction for 8962the function code 2 along with interception and forwarding of both the 8963PTF instruction with function codes 0 or 1 and the STSI(15,1,x) 8964instruction to the userland hypervisor. 8965 8966The stfle facility 11, CPU Topology facility, should not be indicated 8967to the guest without this capability. 8968 8969When this capability is present, KVM provides a new attribute group 8970on vm fd, KVM_S390_VM_CPU_TOPOLOGY. 8971This new attribute allows to get, set or clear the Modified Change 8972Topology Report (MTCR) bit of the SCA through the kvm_device_attr 8973structure. 8974 8975When getting the Modified Change Topology Report value, the attr->addr 8976must point to a byte where the value will be stored or retrieved from. 8977 89788.41 KVM_CAP_VM_TYPES 8979--------------------- 8980 8981:Architectures: x86 8982:Type: system ioctl 8983 8984This capability returns a bitmap of support VM types. The 1-setting of bit @n 8985means the VM type with value @n is supported. Possible values of @n are:: 8986 8987 #define KVM_X86_DEFAULT_VM 0 8988 #define KVM_X86_SW_PROTECTED_VM 1 8989 #define KVM_X86_SEV_VM 2 8990 #define KVM_X86_SEV_ES_VM 3 8991 8992Note, KVM_X86_SW_PROTECTED_VM is currently only for development and testing. 8993Do not use KVM_X86_SW_PROTECTED_VM for "real" VMs, and especially not in 8994production. The behavior and effective ABI for software-protected VMs is 8995unstable. 8996 89978.42 KVM_CAP_PPC_RPT_INVALIDATE 8998------------------------------- 8999 9000:Architectures: ppc 9001 9002This capability indicates that the kernel is capable of handling 9003H_RPT_INVALIDATE hcall. 9004 9005In order to enable the use of H_RPT_INVALIDATE in the guest, 9006user space might have to advertise it for the guest. For example, 9007IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is 9008present in the "ibm,hypertas-functions" device-tree property. 9009 9010This capability is enabled for hypervisors on platforms like POWER9 9011that support radix MMU. 9012 90138.43 KVM_CAP_PPC_AIL_MODE_3 9014--------------------------- 9015 9016:Architectures: ppc 9017 9018This capability indicates that the kernel supports the mode 3 setting for the 9019"Address Translation Mode on Interrupt" aka "Alternate Interrupt Location" 9020resource that is controlled with the H_SET_MODE hypercall. 9021 9022This capability allows a guest kernel to use a better-performance mode for 9023handling interrupts and system calls. 9024 90258.44 KVM_CAP_MEMORY_FAULT_INFO 9026------------------------------ 9027 9028:Architectures: x86 9029 9030The presence of this capability indicates that KVM_RUN will fill 9031kvm_run.memory_fault if KVM cannot resolve a guest page fault VM-Exit, e.g. if 9032there is a valid memslot but no backing VMA for the corresponding host virtual 9033address. 9034 9035The information in kvm_run.memory_fault is valid if and only if KVM_RUN returns 9036an error with errno=EFAULT or errno=EHWPOISON *and* kvm_run.exit_reason is set 9037to KVM_EXIT_MEMORY_FAULT. 9038 9039Note: Userspaces which attempt to resolve memory faults so that they can retry 9040KVM_RUN are encouraged to guard against repeatedly receiving the same 9041error/annotated fault. 9042 9043See KVM_EXIT_MEMORY_FAULT for more information. 9044 90458.45 KVM_CAP_X86_GUEST_MODE 9046--------------------------- 9047 9048:Architectures: x86 9049 9050The presence of this capability indicates that KVM_RUN will update the 9051KVM_RUN_X86_GUEST_MODE bit in kvm_run.flags to indicate whether the 9052vCPU was executing nested guest code when it exited. 9053 9054KVM exits with the register state of either the L1 or L2 guest 9055depending on which executed at the time of an exit. Userspace must 9056take care to differentiate between these cases. 9057 90589. Known KVM API problems 9059========================= 9060 9061In some cases, KVM's API has some inconsistencies or common pitfalls 9062that userspace need to be aware of. This section details some of 9063these issues. 9064 9065Most of them are architecture specific, so the section is split by 9066architecture. 9067 90689.1. x86 9069-------- 9070 9071``KVM_GET_SUPPORTED_CPUID`` issues 9072^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 9073 9074In general, ``KVM_GET_SUPPORTED_CPUID`` is designed so that it is possible 9075to take its result and pass it directly to ``KVM_SET_CPUID2``. This section 9076documents some cases in which that requires some care. 9077 9078Local APIC features 9079~~~~~~~~~~~~~~~~~~~ 9080 9081CPU[EAX=1]:ECX[21] (X2APIC) is reported by ``KVM_GET_SUPPORTED_CPUID``, 9082but it can only be enabled if ``KVM_CREATE_IRQCHIP`` or 9083``KVM_ENABLE_CAP(KVM_CAP_IRQCHIP_SPLIT)`` are used to enable in-kernel emulation of 9084the local APIC. 9085 9086The same is true for the ``KVM_FEATURE_PV_UNHALT`` paravirtualized feature. 9087 9088On older versions of Linux, CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by 9089``KVM_GET_SUPPORTED_CPUID``, but it can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` 9090is present and the kernel has enabled in-kernel emulation of the local APIC. 9091On newer versions, ``KVM_GET_SUPPORTED_CPUID`` does report the bit as available. 9092 9093CPU topology 9094~~~~~~~~~~~~ 9095 9096Several CPUID values include topology information for the host CPU: 90970x0b and 0x1f for Intel systems, 0x8000001e for AMD systems. Different 9098versions of KVM return different values for this information and userspace 9099should not rely on it. Currently they return all zeroes. 9100 9101If userspace wishes to set up a guest topology, it should be careful that 9102the values of these three leaves differ for each CPU. In particular, 9103the APIC ID is found in EDX for all subleaves of 0x0b and 0x1f, and in EAX 9104for 0x8000001e; the latter also encodes the core id and node id in bits 91057:0 of EBX and ECX respectively. 9106 9107Obsolete ioctls and capabilities 9108^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 9109 9110KVM_CAP_DISABLE_QUIRKS does not let userspace know which quirks are actually 9111available. Use ``KVM_CHECK_EXTENSION(KVM_CAP_DISABLE_QUIRKS2)`` instead if 9112available. 9113 9114Ordering of KVM_GET_*/KVM_SET_* ioctls 9115^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 9116 9117TBD 9118