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 1232Calling this ioctl on a vCPU that hasn't been initialized will return 1233-ENOEXEC. 1234 1235:: 1236 1237 struct kvm_vcpu_events { 1238 struct { 1239 __u8 serror_pending; 1240 __u8 serror_has_esr; 1241 __u8 ext_dabt_pending; 1242 /* Align it to 8 bytes */ 1243 __u8 pad[5]; 1244 __u64 serror_esr; 1245 } exception; 1246 __u32 reserved[12]; 1247 }; 1248 12494.32 KVM_SET_VCPU_EVENTS 1250------------------------ 1251 1252:Capability: KVM_CAP_VCPU_EVENTS 1253:Extended by: KVM_CAP_INTR_SHADOW 1254:Architectures: x86, arm64 1255:Type: vcpu ioctl 1256:Parameters: struct kvm_vcpu_events (in) 1257:Returns: 0 on success, -1 on error 1258 1259X86: 1260^^^^ 1261 1262Set pending exceptions, interrupts, and NMIs as well as related states of the 1263vcpu. 1264 1265See KVM_GET_VCPU_EVENTS for the data structure. 1266 1267Fields that may be modified asynchronously by running VCPUs can be excluded 1268from the update. These fields are nmi.pending, sipi_vector, smi.smm, 1269smi.pending. Keep the corresponding bits in the flags field cleared to 1270suppress overwriting the current in-kernel state. The bits are: 1271 1272=============================== ================================== 1273KVM_VCPUEVENT_VALID_NMI_PENDING transfer nmi.pending to the kernel 1274KVM_VCPUEVENT_VALID_SIPI_VECTOR transfer sipi_vector 1275KVM_VCPUEVENT_VALID_SMM transfer the smi sub-struct. 1276=============================== ================================== 1277 1278If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in 1279the flags field to signal that interrupt.shadow contains a valid state and 1280shall be written into the VCPU. 1281 1282KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available. 1283 1284If KVM_CAP_EXCEPTION_PAYLOAD is enabled, KVM_VCPUEVENT_VALID_PAYLOAD 1285can be set in the flags field to signal that the 1286exception_has_payload, exception_payload, and exception.pending fields 1287contain a valid state and shall be written into the VCPU. 1288 1289If KVM_CAP_X86_TRIPLE_FAULT_EVENT is enabled, KVM_VCPUEVENT_VALID_TRIPLE_FAULT 1290can be set in flags field to signal that the triple_fault field contains 1291a valid state and shall be written into the VCPU. 1292 1293ARM64: 1294^^^^^^ 1295 1296User space may need to inject several types of events to the guest. 1297 1298Set the pending SError exception state for this VCPU. It is not possible to 1299'cancel' an Serror that has been made pending. 1300 1301If the guest performed an access to I/O memory which could not be handled by 1302userspace, for example because of missing instruction syndrome decode 1303information or because there is no device mapped at the accessed IPA, then 1304userspace can ask the kernel to inject an external abort using the address 1305from the exiting fault on the VCPU. It is a programming error to set 1306ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO or 1307KVM_EXIT_ARM_NISV. This feature is only available if the system supports 1308KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which provides commonality in 1309how userspace reports accesses for the above cases to guests, across different 1310userspace implementations. Nevertheless, userspace can still emulate all Arm 1311exceptions by manipulating individual registers using the KVM_SET_ONE_REG API. 1312 1313See KVM_GET_VCPU_EVENTS for the data structure. 1314 1315Calling this ioctl on a vCPU that hasn't been initialized will return 1316-ENOEXEC. 1317 13184.33 KVM_GET_DEBUGREGS 1319---------------------- 1320 1321:Capability: KVM_CAP_DEBUGREGS 1322:Architectures: x86 1323:Type: vcpu ioctl 1324:Parameters: struct kvm_debugregs (out) 1325:Returns: 0 on success, -1 on error 1326 1327Reads debug registers from the vcpu. 1328 1329:: 1330 1331 struct kvm_debugregs { 1332 __u64 db[4]; 1333 __u64 dr6; 1334 __u64 dr7; 1335 __u64 flags; 1336 __u64 reserved[9]; 1337 }; 1338 1339 13404.34 KVM_SET_DEBUGREGS 1341---------------------- 1342 1343:Capability: KVM_CAP_DEBUGREGS 1344:Architectures: x86 1345:Type: vcpu ioctl 1346:Parameters: struct kvm_debugregs (in) 1347:Returns: 0 on success, -1 on error 1348 1349Writes debug registers into the vcpu. 1350 1351See KVM_GET_DEBUGREGS for the data structure. The flags field is unused 1352yet and must be cleared on entry. 1353 1354 13554.35 KVM_SET_USER_MEMORY_REGION 1356------------------------------- 1357 1358:Capability: KVM_CAP_USER_MEMORY 1359:Architectures: all 1360:Type: vm ioctl 1361:Parameters: struct kvm_userspace_memory_region (in) 1362:Returns: 0 on success, -1 on error 1363 1364:: 1365 1366 struct kvm_userspace_memory_region { 1367 __u32 slot; 1368 __u32 flags; 1369 __u64 guest_phys_addr; 1370 __u64 memory_size; /* bytes */ 1371 __u64 userspace_addr; /* start of the userspace allocated memory */ 1372 }; 1373 1374 /* for kvm_userspace_memory_region::flags */ 1375 #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) 1376 #define KVM_MEM_READONLY (1UL << 1) 1377 1378This ioctl allows the user to create, modify or delete a guest physical 1379memory slot. Bits 0-15 of "slot" specify the slot id and this value 1380should be less than the maximum number of user memory slots supported per 1381VM. The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS. 1382Slots may not overlap in guest physical address space. 1383 1384If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot" 1385specifies the address space which is being modified. They must be 1386less than the value that KVM_CHECK_EXTENSION returns for the 1387KVM_CAP_MULTI_ADDRESS_SPACE capability. Slots in separate address spaces 1388are unrelated; the restriction on overlapping slots only applies within 1389each address space. 1390 1391Deleting a slot is done by passing zero for memory_size. When changing 1392an existing slot, it may be moved in the guest physical memory space, 1393or its flags may be modified, but it may not be resized. 1394 1395Memory for the region is taken starting at the address denoted by the 1396field userspace_addr, which must point at user addressable memory for 1397the entire memory slot size. Any object may back this memory, including 1398anonymous memory, ordinary files, and hugetlbfs. 1399 1400On architectures that support a form of address tagging, userspace_addr must 1401be an untagged address. 1402 1403It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr 1404be identical. This allows large pages in the guest to be backed by large 1405pages in the host. 1406 1407The flags field supports two flags: KVM_MEM_LOG_DIRTY_PAGES and 1408KVM_MEM_READONLY. The former can be set to instruct KVM to keep track of 1409writes to memory within the slot. See KVM_GET_DIRTY_LOG ioctl to know how to 1410use it. The latter can be set, if KVM_CAP_READONLY_MEM capability allows it, 1411to make a new slot read-only. In this case, writes to this memory will be 1412posted to userspace as KVM_EXIT_MMIO exits. 1413 1414When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of 1415the memory region are automatically reflected into the guest. For example, an 1416mmap() that affects the region will be made visible immediately. Another 1417example is madvise(MADV_DROP). 1418 1419For TDX guest, deleting/moving memory region loses guest memory contents. 1420Read only region isn't supported. Only as-id 0 is supported. 1421 1422Note: On arm64, a write generated by the page-table walker (to update 1423the Access and Dirty flags, for example) never results in a 1424KVM_EXIT_MMIO exit when the slot has the KVM_MEM_READONLY flag. This 1425is because KVM cannot provide the data that would be written by the 1426page-table walker, making it impossible to emulate the access. 1427Instead, an abort (data abort if the cause of the page-table update 1428was a load or a store, instruction abort if it was an instruction 1429fetch) is injected in the guest. 1430 1431S390: 1432^^^^^ 1433 1434Returns -EINVAL or -EEXIST if the VM has the KVM_VM_S390_UCONTROL flag set. 1435Returns -EINVAL if called on a protected VM. 1436 14374.36 KVM_SET_TSS_ADDR 1438--------------------- 1439 1440:Capability: KVM_CAP_SET_TSS_ADDR 1441:Architectures: x86 1442:Type: vm ioctl 1443:Parameters: unsigned long tss_address (in) 1444:Returns: 0 on success, -1 on error 1445 1446This ioctl defines the physical address of a three-page region in the guest 1447physical address space. The region must be within the first 4GB of the 1448guest physical address space and must not conflict with any memory slot 1449or any mmio address. The guest may malfunction if it accesses this memory 1450region. 1451 1452This ioctl is required on Intel-based hosts. This is needed on Intel hardware 1453because of a quirk in the virtualization implementation (see the internals 1454documentation when it pops into existence). 1455 1456 1457.. _KVM_ENABLE_CAP: 1458 14594.37 KVM_ENABLE_CAP 1460------------------- 1461 1462:Capability: KVM_CAP_ENABLE_CAP 1463:Architectures: mips, ppc, s390, x86, loongarch 1464:Type: vcpu ioctl 1465:Parameters: struct kvm_enable_cap (in) 1466:Returns: 0 on success; -1 on error 1467 1468:Capability: KVM_CAP_ENABLE_CAP_VM 1469:Architectures: all 1470:Type: vm ioctl 1471:Parameters: struct kvm_enable_cap (in) 1472:Returns: 0 on success; -1 on error 1473 1474.. note:: 1475 1476 Not all extensions are enabled by default. Using this ioctl the application 1477 can enable an extension, making it available to the guest. 1478 1479On systems that do not support this ioctl, it always fails. On systems that 1480do support it, it only works for extensions that are supported for enablement. 1481 1482To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should 1483be used. 1484 1485:: 1486 1487 struct kvm_enable_cap { 1488 /* in */ 1489 __u32 cap; 1490 1491The capability that is supposed to get enabled. 1492 1493:: 1494 1495 __u32 flags; 1496 1497A bitfield indicating future enhancements. Has to be 0 for now. 1498 1499:: 1500 1501 __u64 args[4]; 1502 1503Arguments for enabling a feature. If a feature needs initial values to 1504function properly, this is the place to put them. 1505 1506:: 1507 1508 __u8 pad[64]; 1509 }; 1510 1511The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl 1512for vm-wide capabilities. 1513 15144.38 KVM_GET_MP_STATE 1515--------------------- 1516 1517:Capability: KVM_CAP_MP_STATE 1518:Architectures: x86, s390, arm64, riscv, loongarch 1519:Type: vcpu ioctl 1520:Parameters: struct kvm_mp_state (out) 1521:Returns: 0 on success; -1 on error 1522 1523:: 1524 1525 struct kvm_mp_state { 1526 __u32 mp_state; 1527 }; 1528 1529Returns the vcpu's current "multiprocessing state" (though also valid on 1530uniprocessor guests). 1531 1532Possible values are: 1533 1534 ========================== =============================================== 1535 KVM_MP_STATE_RUNNABLE the vcpu is currently running 1536 [x86,arm64,riscv,loongarch] 1537 KVM_MP_STATE_UNINITIALIZED the vcpu is an application processor (AP) 1538 which has not yet received an INIT signal [x86] 1539 KVM_MP_STATE_INIT_RECEIVED the vcpu has received an INIT signal, and is 1540 now ready for a SIPI [x86] 1541 KVM_MP_STATE_HALTED the vcpu has executed a HLT instruction and 1542 is waiting for an interrupt [x86] 1543 KVM_MP_STATE_SIPI_RECEIVED the vcpu has just received a SIPI (vector 1544 accessible via KVM_GET_VCPU_EVENTS) [x86] 1545 KVM_MP_STATE_STOPPED the vcpu is stopped [s390,arm64,riscv] 1546 KVM_MP_STATE_CHECK_STOP the vcpu is in a special error state [s390] 1547 KVM_MP_STATE_OPERATING the vcpu is operating (running or halted) 1548 [s390] 1549 KVM_MP_STATE_LOAD the vcpu is in a special load/startup state 1550 [s390] 1551 KVM_MP_STATE_SUSPENDED the vcpu is in a suspend state and is waiting 1552 for a wakeup event [arm64] 1553 ========================== =============================================== 1554 1555On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an 1556in-kernel irqchip, the multiprocessing state must be maintained by userspace on 1557these architectures. 1558 1559For arm64: 1560^^^^^^^^^^ 1561 1562If a vCPU is in the KVM_MP_STATE_SUSPENDED state, KVM will emulate the 1563architectural execution of a WFI instruction. 1564 1565If a wakeup event is recognized, KVM will exit to userspace with a 1566KVM_SYSTEM_EVENT exit, where the event type is KVM_SYSTEM_EVENT_WAKEUP. If 1567userspace wants to honor the wakeup, it must set the vCPU's MP state to 1568KVM_MP_STATE_RUNNABLE. If it does not, KVM will continue to await a wakeup 1569event in subsequent calls to KVM_RUN. 1570 1571.. warning:: 1572 1573 If userspace intends to keep the vCPU in a SUSPENDED state, it is 1574 strongly recommended that userspace take action to suppress the 1575 wakeup event (such as masking an interrupt). Otherwise, subsequent 1576 calls to KVM_RUN will immediately exit with a KVM_SYSTEM_EVENT_WAKEUP 1577 event and inadvertently waste CPU cycles. 1578 1579 Additionally, if userspace takes action to suppress a wakeup event, 1580 it is strongly recommended that it also restores the vCPU to its 1581 original state when the vCPU is made RUNNABLE again. For example, 1582 if userspace masked a pending interrupt to suppress the wakeup, 1583 the interrupt should be unmasked before returning control to the 1584 guest. 1585 1586For riscv: 1587^^^^^^^^^^ 1588 1589The only states that are valid are KVM_MP_STATE_STOPPED and 1590KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not. 1591 1592On LoongArch, only the KVM_MP_STATE_RUNNABLE state is used to reflect 1593whether the vcpu is runnable. 1594 15954.39 KVM_SET_MP_STATE 1596--------------------- 1597 1598:Capability: KVM_CAP_MP_STATE 1599:Architectures: x86, s390, arm64, riscv, loongarch 1600:Type: vcpu ioctl 1601:Parameters: struct kvm_mp_state (in) 1602:Returns: 0 on success; -1 on error 1603 1604Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for 1605arguments. 1606 1607On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an 1608in-kernel irqchip, the multiprocessing state must be maintained by userspace on 1609these architectures. 1610 1611For arm64/riscv: 1612^^^^^^^^^^^^^^^^ 1613 1614The only states that are valid are KVM_MP_STATE_STOPPED and 1615KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not. 1616 1617On LoongArch, only the KVM_MP_STATE_RUNNABLE state is used to reflect 1618whether the vcpu is runnable. 1619 16204.40 KVM_SET_IDENTITY_MAP_ADDR 1621------------------------------ 1622 1623:Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR 1624:Architectures: x86 1625:Type: vm ioctl 1626:Parameters: unsigned long identity (in) 1627:Returns: 0 on success, -1 on error 1628 1629This ioctl defines the physical address of a one-page region in the guest 1630physical address space. The region must be within the first 4GB of the 1631guest physical address space and must not conflict with any memory slot 1632or any mmio address. The guest may malfunction if it accesses this memory 1633region. 1634 1635Setting the address to 0 will result in resetting the address to its default 1636(0xfffbc000). 1637 1638This ioctl is required on Intel-based hosts. This is needed on Intel hardware 1639because of a quirk in the virtualization implementation (see the internals 1640documentation when it pops into existence). 1641 1642Fails if any VCPU has already been created. 1643 16444.41 KVM_SET_BOOT_CPU_ID 1645------------------------ 1646 1647:Capability: KVM_CAP_SET_BOOT_CPU_ID 1648:Architectures: x86 1649:Type: vm ioctl 1650:Parameters: unsigned long vcpu_id 1651:Returns: 0 on success, -1 on error 1652 1653Define which vcpu is the Bootstrap Processor (BSP). Values are the same 1654as the vcpu id in KVM_CREATE_VCPU. If this ioctl is not called, the default 1655is vcpu 0. This ioctl has to be called before vcpu creation, 1656otherwise it will return EBUSY error. 1657 1658 16594.42 KVM_GET_XSAVE 1660------------------ 1661 1662:Capability: KVM_CAP_XSAVE 1663:Architectures: x86 1664:Type: vcpu ioctl 1665:Parameters: struct kvm_xsave (out) 1666:Returns: 0 on success, -1 on error 1667 1668 1669:: 1670 1671 struct kvm_xsave { 1672 __u32 region[1024]; 1673 __u32 extra[0]; 1674 }; 1675 1676This ioctl would copy current vcpu's xsave struct to the userspace. 1677 1678 16794.43 KVM_SET_XSAVE 1680------------------ 1681 1682:Capability: KVM_CAP_XSAVE and KVM_CAP_XSAVE2 1683:Architectures: x86 1684:Type: vcpu ioctl 1685:Parameters: struct kvm_xsave (in) 1686:Returns: 0 on success, -1 on error 1687 1688:: 1689 1690 1691 struct kvm_xsave { 1692 __u32 region[1024]; 1693 __u32 extra[0]; 1694 }; 1695 1696This ioctl would copy userspace's xsave struct to the kernel. It copies 1697as many bytes as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2), 1698when invoked on the vm file descriptor. The size value returned by 1699KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) will always be at least 4096. 1700Currently, it is only greater than 4096 if a dynamic feature has been 1701enabled with ``arch_prctl()``, but this may change in the future. 1702 1703The offsets of the state save areas in struct kvm_xsave follow the 1704contents of CPUID leaf 0xD on the host. 1705 1706 17074.44 KVM_GET_XCRS 1708----------------- 1709 1710:Capability: KVM_CAP_XCRS 1711:Architectures: x86 1712:Type: vcpu ioctl 1713:Parameters: struct kvm_xcrs (out) 1714:Returns: 0 on success, -1 on error 1715 1716:: 1717 1718 struct kvm_xcr { 1719 __u32 xcr; 1720 __u32 reserved; 1721 __u64 value; 1722 }; 1723 1724 struct kvm_xcrs { 1725 __u32 nr_xcrs; 1726 __u32 flags; 1727 struct kvm_xcr xcrs[KVM_MAX_XCRS]; 1728 __u64 padding[16]; 1729 }; 1730 1731This ioctl would copy current vcpu's xcrs to the userspace. 1732 1733 17344.45 KVM_SET_XCRS 1735----------------- 1736 1737:Capability: KVM_CAP_XCRS 1738:Architectures: x86 1739:Type: vcpu ioctl 1740:Parameters: struct kvm_xcrs (in) 1741:Returns: 0 on success, -1 on error 1742 1743:: 1744 1745 struct kvm_xcr { 1746 __u32 xcr; 1747 __u32 reserved; 1748 __u64 value; 1749 }; 1750 1751 struct kvm_xcrs { 1752 __u32 nr_xcrs; 1753 __u32 flags; 1754 struct kvm_xcr xcrs[KVM_MAX_XCRS]; 1755 __u64 padding[16]; 1756 }; 1757 1758This ioctl would set vcpu's xcr to the value userspace specified. 1759 1760 17614.46 KVM_GET_SUPPORTED_CPUID 1762---------------------------- 1763 1764:Capability: KVM_CAP_EXT_CPUID 1765:Architectures: x86 1766:Type: system ioctl 1767:Parameters: struct kvm_cpuid2 (in/out) 1768:Returns: 0 on success, -1 on error 1769 1770:: 1771 1772 struct kvm_cpuid2 { 1773 __u32 nent; 1774 __u32 padding; 1775 struct kvm_cpuid_entry2 entries[0]; 1776 }; 1777 1778 #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) 1779 #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) /* deprecated */ 1780 #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) /* deprecated */ 1781 1782 struct kvm_cpuid_entry2 { 1783 __u32 function; 1784 __u32 index; 1785 __u32 flags; 1786 __u32 eax; 1787 __u32 ebx; 1788 __u32 ecx; 1789 __u32 edx; 1790 __u32 padding[3]; 1791 }; 1792 1793This ioctl returns x86 cpuid features which are supported by both the 1794hardware and kvm in its default configuration. Userspace can use the 1795information returned by this ioctl to construct cpuid information (for 1796KVM_SET_CPUID2) that is consistent with hardware, kernel, and 1797userspace capabilities, and with user requirements (for example, the 1798user may wish to constrain cpuid to emulate older hardware, or for 1799feature consistency across a cluster). 1800 1801Dynamically-enabled feature bits need to be requested with 1802``arch_prctl()`` before calling this ioctl. Feature bits that have not 1803been requested are excluded from the result. 1804 1805Note that certain capabilities, such as KVM_CAP_X86_DISABLE_EXITS, may 1806expose cpuid features (e.g. MONITOR) which are not supported by kvm in 1807its default configuration. If userspace enables such capabilities, it 1808is responsible for modifying the results of this ioctl appropriately. 1809 1810Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure 1811with the 'nent' field indicating the number of entries in the variable-size 1812array 'entries'. If the number of entries is too low to describe the cpu 1813capabilities, an error (E2BIG) is returned. If the number is too high, 1814the 'nent' field is adjusted and an error (ENOMEM) is returned. If the 1815number is just right, the 'nent' field is adjusted to the number of valid 1816entries in the 'entries' array, which is then filled. 1817 1818The entries returned are the host cpuid as returned by the cpuid instruction, 1819with unknown or unsupported features masked out. Some features (for example, 1820x2apic), may not be present in the host cpu, but are exposed by kvm if it can 1821emulate them efficiently. The fields in each entry are defined as follows: 1822 1823 function: 1824 the eax value used to obtain the entry 1825 1826 index: 1827 the ecx value used to obtain the entry (for entries that are 1828 affected by ecx) 1829 1830 flags: 1831 an OR of zero or more of the following: 1832 1833 KVM_CPUID_FLAG_SIGNIFCANT_INDEX: 1834 if the index field is valid 1835 1836 eax, ebx, ecx, edx: 1837 the values returned by the cpuid instruction for 1838 this function/index combination 1839 1840x2APIC (CPUID leaf 1, ecx[21) and TSC deadline timer (CPUID leaf 1, ecx[24]) 1841may be returned as true, but they depend on KVM_CREATE_IRQCHIP for in-kernel 1842emulation of the local APIC. TSC deadline timer support is also reported via:: 1843 1844 ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER) 1845 1846if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the 1847feature in userspace, then you can enable the feature for KVM_SET_CPUID2. 1848 1849Enabling x2APIC in KVM_SET_CPUID2 requires KVM_CREATE_IRQCHIP as KVM doesn't 1850support forwarding x2APIC MSR accesses to userspace, i.e. KVM does not support 1851emulating x2APIC in userspace. 1852 18534.47 KVM_PPC_GET_PVINFO 1854----------------------- 1855 1856:Capability: KVM_CAP_PPC_GET_PVINFO 1857:Architectures: ppc 1858:Type: vm ioctl 1859:Parameters: struct kvm_ppc_pvinfo (out) 1860:Returns: 0 on success, !0 on error 1861 1862:: 1863 1864 struct kvm_ppc_pvinfo { 1865 __u32 flags; 1866 __u32 hcall[4]; 1867 __u8 pad[108]; 1868 }; 1869 1870This ioctl fetches PV specific information that need to be passed to the guest 1871using the device tree or other means from vm context. 1872 1873The hcall array defines 4 instructions that make up a hypercall. 1874 1875If any additional field gets added to this structure later on, a bit for that 1876additional piece of information will be set in the flags bitmap. 1877 1878The flags bitmap is defined as:: 1879 1880 /* the host supports the ePAPR idle hcall 1881 #define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) 1882 18834.52 KVM_SET_GSI_ROUTING 1884------------------------ 1885 1886:Capability: KVM_CAP_IRQ_ROUTING 1887:Architectures: x86 s390 arm64 1888:Type: vm ioctl 1889:Parameters: struct kvm_irq_routing (in) 1890:Returns: 0 on success, -1 on error 1891 1892Sets the GSI routing table entries, overwriting any previously set entries. 1893 1894On arm64, GSI routing has the following limitation: 1895 1896- GSI routing does not apply to KVM_IRQ_LINE but only to KVM_IRQFD. 1897 1898:: 1899 1900 struct kvm_irq_routing { 1901 __u32 nr; 1902 __u32 flags; 1903 struct kvm_irq_routing_entry entries[0]; 1904 }; 1905 1906No flags are specified so far, the corresponding field must be set to zero. 1907 1908:: 1909 1910 struct kvm_irq_routing_entry { 1911 __u32 gsi; 1912 __u32 type; 1913 __u32 flags; 1914 __u32 pad; 1915 union { 1916 struct kvm_irq_routing_irqchip irqchip; 1917 struct kvm_irq_routing_msi msi; 1918 struct kvm_irq_routing_s390_adapter adapter; 1919 struct kvm_irq_routing_hv_sint hv_sint; 1920 struct kvm_irq_routing_xen_evtchn xen_evtchn; 1921 __u32 pad[8]; 1922 } u; 1923 }; 1924 1925 /* gsi routing entry types */ 1926 #define KVM_IRQ_ROUTING_IRQCHIP 1 1927 #define KVM_IRQ_ROUTING_MSI 2 1928 #define KVM_IRQ_ROUTING_S390_ADAPTER 3 1929 #define KVM_IRQ_ROUTING_HV_SINT 4 1930 #define KVM_IRQ_ROUTING_XEN_EVTCHN 5 1931 1932On s390, adding a KVM_IRQ_ROUTING_S390_ADAPTER is rejected on ucontrol VMs with 1933error -EINVAL. 1934 1935flags: 1936 1937- KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry 1938 type, specifies that the devid field contains a valid value. The per-VM 1939 KVM_CAP_MSI_DEVID capability advertises the requirement to provide 1940 the device ID. If this capability is not available, userspace should 1941 never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail. 1942- zero otherwise 1943 1944:: 1945 1946 struct kvm_irq_routing_irqchip { 1947 __u32 irqchip; 1948 __u32 pin; 1949 }; 1950 1951 struct kvm_irq_routing_msi { 1952 __u32 address_lo; 1953 __u32 address_hi; 1954 __u32 data; 1955 union { 1956 __u32 pad; 1957 __u32 devid; 1958 }; 1959 }; 1960 1961If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier 1962for the device that wrote the MSI message. For PCI, this is usually a 1963BDF identifier in the lower 16 bits. 1964 1965On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS 1966feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled, 1967address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of 1968address_hi must be zero. 1969 1970:: 1971 1972 struct kvm_irq_routing_s390_adapter { 1973 __u64 ind_addr; 1974 __u64 summary_addr; 1975 __u64 ind_offset; 1976 __u32 summary_offset; 1977 __u32 adapter_id; 1978 }; 1979 1980 struct kvm_irq_routing_hv_sint { 1981 __u32 vcpu; 1982 __u32 sint; 1983 }; 1984 1985 struct kvm_irq_routing_xen_evtchn { 1986 __u32 port; 1987 __u32 vcpu; 1988 __u32 priority; 1989 }; 1990 1991 1992When KVM_CAP_XEN_HVM includes the KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL bit 1993in its indication of supported features, routing to Xen event channels 1994is supported. Although the priority field is present, only the value 1995KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL is supported, which means delivery by 19962 level event channels. FIFO event channel support may be added in 1997the future. 1998 1999 20004.55 KVM_SET_TSC_KHZ 2001-------------------- 2002 2003:Capability: KVM_CAP_TSC_CONTROL / KVM_CAP_VM_TSC_CONTROL 2004:Architectures: x86 2005:Type: vcpu ioctl / vm ioctl 2006:Parameters: virtual tsc_khz 2007:Returns: 0 on success, -1 on error 2008 2009Specifies the tsc frequency for the virtual machine. The unit of the 2010frequency is KHz. 2011 2012If the KVM_CAP_VM_TSC_CONTROL capability is advertised, this can also 2013be used as a vm ioctl to set the initial tsc frequency of subsequently 2014created vCPUs. Note, the vm ioctl is only allowed prior to creating vCPUs. 2015 2016For TSC protected Confidential Computing (CoCo) VMs where TSC frequency 2017is configured once at VM scope and remains unchanged during VM's 2018lifetime, the vm ioctl should be used to configure the TSC frequency 2019and the vcpu ioctl is not supported. 2020 2021Example of such CoCo VMs: TDX guests. 2022 20234.56 KVM_GET_TSC_KHZ 2024-------------------- 2025 2026:Capability: KVM_CAP_GET_TSC_KHZ / KVM_CAP_VM_TSC_CONTROL 2027:Architectures: x86 2028:Type: vcpu ioctl / vm ioctl 2029:Parameters: none 2030:Returns: virtual tsc-khz on success, negative value on error 2031 2032Returns the tsc frequency of the guest. The unit of the return value is 2033KHz. If the host has unstable tsc this ioctl returns -EIO instead as an 2034error. 2035 2036 20374.57 KVM_GET_LAPIC 2038------------------ 2039 2040:Capability: KVM_CAP_IRQCHIP 2041:Architectures: x86 2042:Type: vcpu ioctl 2043:Parameters: struct kvm_lapic_state (out) 2044:Returns: 0 on success, -1 on error 2045 2046:: 2047 2048 #define KVM_APIC_REG_SIZE 0x400 2049 struct kvm_lapic_state { 2050 char regs[KVM_APIC_REG_SIZE]; 2051 }; 2052 2053Reads the Local APIC registers and copies them into the input argument. The 2054data format and layout are the same as documented in the architecture manual. 2055 2056If KVM_X2APIC_API_USE_32BIT_IDS feature of KVM_CAP_X2APIC_API is 2057enabled, then the format of APIC_ID register depends on the APIC mode 2058(reported by MSR_IA32_APICBASE) of its VCPU. x2APIC stores APIC ID in 2059the APIC_ID register (bytes 32-35). xAPIC only allows an 8-bit APIC ID 2060which is stored in bits 31-24 of the APIC register, or equivalently in 2061byte 35 of struct kvm_lapic_state's regs field. KVM_GET_LAPIC must then 2062be called after MSR_IA32_APICBASE has been set with KVM_SET_MSR. 2063 2064If KVM_X2APIC_API_USE_32BIT_IDS feature is disabled, struct kvm_lapic_state 2065always uses xAPIC format. 2066 2067 20684.58 KVM_SET_LAPIC 2069------------------ 2070 2071:Capability: KVM_CAP_IRQCHIP 2072:Architectures: x86 2073:Type: vcpu ioctl 2074:Parameters: struct kvm_lapic_state (in) 2075:Returns: 0 on success, -1 on error 2076 2077:: 2078 2079 #define KVM_APIC_REG_SIZE 0x400 2080 struct kvm_lapic_state { 2081 char regs[KVM_APIC_REG_SIZE]; 2082 }; 2083 2084Copies the input argument into the Local APIC registers. The data format 2085and layout are the same as documented in the architecture manual. 2086 2087The format of the APIC ID register (bytes 32-35 of struct kvm_lapic_state's 2088regs field) depends on the state of the KVM_CAP_X2APIC_API capability. 2089See the note in KVM_GET_LAPIC. 2090 2091 20924.59 KVM_IOEVENTFD 2093------------------ 2094 2095:Capability: KVM_CAP_IOEVENTFD 2096:Architectures: all 2097:Type: vm ioctl 2098:Parameters: struct kvm_ioeventfd (in) 2099:Returns: 0 on success, !0 on error 2100 2101This ioctl attaches or detaches an ioeventfd to a legal pio/mmio address 2102within the guest. A guest write in the registered address will signal the 2103provided event instead of triggering an exit. 2104 2105:: 2106 2107 struct kvm_ioeventfd { 2108 __u64 datamatch; 2109 __u64 addr; /* legal pio/mmio address */ 2110 __u32 len; /* 0, 1, 2, 4, or 8 bytes */ 2111 __s32 fd; 2112 __u32 flags; 2113 __u8 pad[36]; 2114 }; 2115 2116For the special case of virtio-ccw devices on s390, the ioevent is matched 2117to a subchannel/virtqueue tuple instead. 2118 2119The following flags are defined:: 2120 2121 #define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch) 2122 #define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio) 2123 #define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign) 2124 #define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \ 2125 (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify) 2126 2127If datamatch flag is set, the event will be signaled only if the written value 2128to the registered address is equal to datamatch in struct kvm_ioeventfd. 2129 2130For virtio-ccw devices, addr contains the subchannel id and datamatch the 2131virtqueue index. 2132 2133With KVM_CAP_IOEVENTFD_ANY_LENGTH, a zero length ioeventfd is allowed, and 2134the kernel will ignore the length of guest write and may get a faster vmexit. 2135The speedup may only apply to specific architectures, but the ioeventfd will 2136work anyway. 2137 21384.60 KVM_DIRTY_TLB 2139------------------ 2140 2141:Capability: KVM_CAP_SW_TLB 2142:Architectures: ppc 2143:Type: vcpu ioctl 2144:Parameters: struct kvm_dirty_tlb (in) 2145:Returns: 0 on success, -1 on error 2146 2147:: 2148 2149 struct kvm_dirty_tlb { 2150 __u64 bitmap; 2151 __u32 num_dirty; 2152 }; 2153 2154This must be called whenever userspace has changed an entry in the shared 2155TLB, prior to calling KVM_RUN on the associated vcpu. 2156 2157The "bitmap" field is the userspace address of an array. This array 2158consists of a number of bits, equal to the total number of TLB entries as 2159determined by the last successful call to ``KVM_ENABLE_CAP(KVM_CAP_SW_TLB)``, 2160rounded up to the nearest multiple of 64. 2161 2162Each bit corresponds to one TLB entry, ordered the same as in the shared TLB 2163array. 2164 2165The array is little-endian: the bit 0 is the least significant bit of the 2166first byte, bit 8 is the least significant bit of the second byte, etc. 2167This avoids any complications with differing word sizes. 2168 2169The "num_dirty" field is a performance hint for KVM to determine whether it 2170should skip processing the bitmap and just invalidate everything. It must 2171be set to the number of set bits in the bitmap. 2172 2173 21744.62 KVM_CREATE_SPAPR_TCE 2175------------------------- 2176 2177:Capability: KVM_CAP_SPAPR_TCE 2178:Architectures: powerpc 2179:Type: vm ioctl 2180:Parameters: struct kvm_create_spapr_tce (in) 2181:Returns: file descriptor for manipulating the created TCE table 2182 2183This creates a virtual TCE (translation control entry) table, which 2184is an IOMMU for PAPR-style virtual I/O. It is used to translate 2185logical addresses used in virtual I/O into guest physical addresses, 2186and provides a scatter/gather capability for PAPR virtual I/O. 2187 2188:: 2189 2190 /* for KVM_CAP_SPAPR_TCE */ 2191 struct kvm_create_spapr_tce { 2192 __u64 liobn; 2193 __u32 window_size; 2194 }; 2195 2196The liobn field gives the logical IO bus number for which to create a 2197TCE table. The window_size field specifies the size of the DMA window 2198which this TCE table will translate - the table will contain one 64 2199bit TCE entry for every 4kiB of the DMA window. 2200 2201When the guest issues an H_PUT_TCE hcall on a liobn for which a TCE 2202table has been created using this ioctl(), the kernel will handle it 2203in real mode, updating the TCE table. H_PUT_TCE calls for other 2204liobns will cause a vm exit and must be handled by userspace. 2205 2206The return value is a file descriptor which can be passed to mmap(2) 2207to map the created TCE table into userspace. This lets userspace read 2208the entries written by kernel-handled H_PUT_TCE calls, and also lets 2209userspace update the TCE table directly which is useful in some 2210circumstances. 2211 2212 22134.64 KVM_NMI 2214------------ 2215 2216:Capability: KVM_CAP_USER_NMI 2217:Architectures: x86 2218:Type: vcpu ioctl 2219:Parameters: none 2220:Returns: 0 on success, -1 on error 2221 2222Queues an NMI on the thread's vcpu. Note this is well defined only 2223when KVM_CREATE_IRQCHIP has not been called, since this is an interface 2224between the virtual cpu core and virtual local APIC. After KVM_CREATE_IRQCHIP 2225has been called, this interface is completely emulated within the kernel. 2226 2227To use this to emulate the LINT1 input with KVM_CREATE_IRQCHIP, use the 2228following algorithm: 2229 2230 - pause the vcpu 2231 - read the local APIC's state (KVM_GET_LAPIC) 2232 - check whether changing LINT1 will queue an NMI (see the LVT entry for LINT1) 2233 - if so, issue KVM_NMI 2234 - resume the vcpu 2235 2236Some guests configure the LINT1 NMI input to cause a panic, aiding in 2237debugging. 2238 2239 22404.65 KVM_S390_UCAS_MAP 2241---------------------- 2242 2243:Capability: KVM_CAP_S390_UCONTROL 2244:Architectures: s390 2245:Type: vcpu ioctl 2246:Parameters: struct kvm_s390_ucas_mapping (in) 2247:Returns: 0 in case of success 2248 2249The parameter is defined like this:: 2250 2251 struct kvm_s390_ucas_mapping { 2252 __u64 user_addr; 2253 __u64 vcpu_addr; 2254 __u64 length; 2255 }; 2256 2257This ioctl maps the memory at "user_addr" with the length "length" to 2258the vcpu's address space starting at "vcpu_addr". All parameters need to 2259be aligned by 1 megabyte. 2260 2261 22624.66 KVM_S390_UCAS_UNMAP 2263------------------------ 2264 2265:Capability: KVM_CAP_S390_UCONTROL 2266:Architectures: s390 2267:Type: vcpu ioctl 2268:Parameters: struct kvm_s390_ucas_mapping (in) 2269:Returns: 0 in case of success 2270 2271The parameter is defined like this:: 2272 2273 struct kvm_s390_ucas_mapping { 2274 __u64 user_addr; 2275 __u64 vcpu_addr; 2276 __u64 length; 2277 }; 2278 2279This ioctl unmaps the memory in the vcpu's address space starting at 2280"vcpu_addr" with the length "length". The field "user_addr" is ignored. 2281All parameters need to be aligned by 1 megabyte. 2282 2283 22844.67 KVM_S390_VCPU_FAULT 2285------------------------ 2286 2287:Capability: KVM_CAP_S390_UCONTROL 2288:Architectures: s390 2289:Type: vcpu ioctl 2290:Parameters: vcpu absolute address (in) 2291:Returns: 0 in case of success 2292 2293This call creates a page table entry on the virtual cpu's address space 2294(for user controlled virtual machines) or the virtual machine's address 2295space (for regular virtual machines). This only works for minor faults, 2296thus it's recommended to access subject memory page via the user page 2297table upfront. This is useful to handle validity intercepts for user 2298controlled virtual machines to fault in the virtual cpu's lowcore pages 2299prior to calling the KVM_RUN ioctl. 2300 2301 23024.68 KVM_SET_ONE_REG 2303-------------------- 2304 2305:Capability: KVM_CAP_ONE_REG 2306:Architectures: all 2307:Type: vcpu ioctl 2308:Parameters: struct kvm_one_reg (in) 2309:Returns: 0 on success, negative value on failure 2310 2311Errors: 2312 2313 ====== ============================================================ 2314 ENOENT no such register 2315 EINVAL invalid register ID, or no such register or used with VMs in 2316 protected virtualization mode on s390 2317 EPERM (arm64) register access not allowed before vcpu finalization 2318 EBUSY (riscv) changing register value not allowed after the vcpu 2319 has run at least once 2320 ====== ============================================================ 2321 2322(These error codes are indicative only: do not rely on a specific error 2323code being returned in a specific situation.) 2324 2325:: 2326 2327 struct kvm_one_reg { 2328 __u64 id; 2329 __u64 addr; 2330 }; 2331 2332Using this ioctl, a single vcpu register can be set to a specific value 2333defined by user space with the passed in struct kvm_one_reg, where id 2334refers to the register identifier as described below and addr is a pointer 2335to a variable with the respective size. There can be architecture agnostic 2336and architecture specific registers. Each have their own range of operation 2337and their own constants and width. To keep track of the implemented 2338registers, find a list below: 2339 2340 ======= =============================== ============ 2341 Arch Register Width (bits) 2342 ======= =============================== ============ 2343 PPC KVM_REG_PPC_HIOR 64 2344 PPC KVM_REG_PPC_IAC1 64 2345 PPC KVM_REG_PPC_IAC2 64 2346 PPC KVM_REG_PPC_IAC3 64 2347 PPC KVM_REG_PPC_IAC4 64 2348 PPC KVM_REG_PPC_DAC1 64 2349 PPC KVM_REG_PPC_DAC2 64 2350 PPC KVM_REG_PPC_DABR 64 2351 PPC KVM_REG_PPC_DSCR 64 2352 PPC KVM_REG_PPC_PURR 64 2353 PPC KVM_REG_PPC_SPURR 64 2354 PPC KVM_REG_PPC_DAR 64 2355 PPC KVM_REG_PPC_DSISR 32 2356 PPC KVM_REG_PPC_AMR 64 2357 PPC KVM_REG_PPC_UAMOR 64 2358 PPC KVM_REG_PPC_MMCR0 64 2359 PPC KVM_REG_PPC_MMCR1 64 2360 PPC KVM_REG_PPC_MMCRA 64 2361 PPC KVM_REG_PPC_MMCR2 64 2362 PPC KVM_REG_PPC_MMCRS 64 2363 PPC KVM_REG_PPC_MMCR3 64 2364 PPC KVM_REG_PPC_SIAR 64 2365 PPC KVM_REG_PPC_SDAR 64 2366 PPC KVM_REG_PPC_SIER 64 2367 PPC KVM_REG_PPC_SIER2 64 2368 PPC KVM_REG_PPC_SIER3 64 2369 PPC KVM_REG_PPC_PMC1 32 2370 PPC KVM_REG_PPC_PMC2 32 2371 PPC KVM_REG_PPC_PMC3 32 2372 PPC KVM_REG_PPC_PMC4 32 2373 PPC KVM_REG_PPC_PMC5 32 2374 PPC KVM_REG_PPC_PMC6 32 2375 PPC KVM_REG_PPC_PMC7 32 2376 PPC KVM_REG_PPC_PMC8 32 2377 PPC KVM_REG_PPC_FPR0 64 2378 ... 2379 PPC KVM_REG_PPC_FPR31 64 2380 PPC KVM_REG_PPC_VR0 128 2381 ... 2382 PPC KVM_REG_PPC_VR31 128 2383 PPC KVM_REG_PPC_VSR0 128 2384 ... 2385 PPC KVM_REG_PPC_VSR31 128 2386 PPC KVM_REG_PPC_FPSCR 64 2387 PPC KVM_REG_PPC_VSCR 32 2388 PPC KVM_REG_PPC_VPA_ADDR 64 2389 PPC KVM_REG_PPC_VPA_SLB 128 2390 PPC KVM_REG_PPC_VPA_DTL 128 2391 PPC KVM_REG_PPC_EPCR 32 2392 PPC KVM_REG_PPC_EPR 32 2393 PPC KVM_REG_PPC_TCR 32 2394 PPC KVM_REG_PPC_TSR 32 2395 PPC KVM_REG_PPC_OR_TSR 32 2396 PPC KVM_REG_PPC_CLEAR_TSR 32 2397 PPC KVM_REG_PPC_MAS0 32 2398 PPC KVM_REG_PPC_MAS1 32 2399 PPC KVM_REG_PPC_MAS2 64 2400 PPC KVM_REG_PPC_MAS7_3 64 2401 PPC KVM_REG_PPC_MAS4 32 2402 PPC KVM_REG_PPC_MAS6 32 2403 PPC KVM_REG_PPC_MMUCFG 32 2404 PPC KVM_REG_PPC_TLB0CFG 32 2405 PPC KVM_REG_PPC_TLB1CFG 32 2406 PPC KVM_REG_PPC_TLB2CFG 32 2407 PPC KVM_REG_PPC_TLB3CFG 32 2408 PPC KVM_REG_PPC_TLB0PS 32 2409 PPC KVM_REG_PPC_TLB1PS 32 2410 PPC KVM_REG_PPC_TLB2PS 32 2411 PPC KVM_REG_PPC_TLB3PS 32 2412 PPC KVM_REG_PPC_EPTCFG 32 2413 PPC KVM_REG_PPC_ICP_STATE 64 2414 PPC KVM_REG_PPC_VP_STATE 128 2415 PPC KVM_REG_PPC_TB_OFFSET 64 2416 PPC KVM_REG_PPC_SPMC1 32 2417 PPC KVM_REG_PPC_SPMC2 32 2418 PPC KVM_REG_PPC_IAMR 64 2419 PPC KVM_REG_PPC_TFHAR 64 2420 PPC KVM_REG_PPC_TFIAR 64 2421 PPC KVM_REG_PPC_TEXASR 64 2422 PPC KVM_REG_PPC_FSCR 64 2423 PPC KVM_REG_PPC_PSPB 32 2424 PPC KVM_REG_PPC_EBBHR 64 2425 PPC KVM_REG_PPC_EBBRR 64 2426 PPC KVM_REG_PPC_BESCR 64 2427 PPC KVM_REG_PPC_TAR 64 2428 PPC KVM_REG_PPC_DPDES 64 2429 PPC KVM_REG_PPC_DAWR 64 2430 PPC KVM_REG_PPC_DAWRX 64 2431 PPC KVM_REG_PPC_CIABR 64 2432 PPC KVM_REG_PPC_IC 64 2433 PPC KVM_REG_PPC_VTB 64 2434 PPC KVM_REG_PPC_CSIGR 64 2435 PPC KVM_REG_PPC_TACR 64 2436 PPC KVM_REG_PPC_TCSCR 64 2437 PPC KVM_REG_PPC_PID 64 2438 PPC KVM_REG_PPC_ACOP 64 2439 PPC KVM_REG_PPC_VRSAVE 32 2440 PPC KVM_REG_PPC_LPCR 32 2441 PPC KVM_REG_PPC_LPCR_64 64 2442 PPC KVM_REG_PPC_PPR 64 2443 PPC KVM_REG_PPC_ARCH_COMPAT 32 2444 PPC KVM_REG_PPC_DABRX 32 2445 PPC KVM_REG_PPC_WORT 64 2446 PPC KVM_REG_PPC_SPRG9 64 2447 PPC KVM_REG_PPC_DBSR 32 2448 PPC KVM_REG_PPC_TIDR 64 2449 PPC KVM_REG_PPC_PSSCR 64 2450 PPC KVM_REG_PPC_DEC_EXPIRY 64 2451 PPC KVM_REG_PPC_PTCR 64 2452 PPC KVM_REG_PPC_HASHKEYR 64 2453 PPC KVM_REG_PPC_HASHPKEYR 64 2454 PPC KVM_REG_PPC_DAWR1 64 2455 PPC KVM_REG_PPC_DAWRX1 64 2456 PPC KVM_REG_PPC_DEXCR 64 2457 PPC KVM_REG_PPC_TM_GPR0 64 2458 ... 2459 PPC KVM_REG_PPC_TM_GPR31 64 2460 PPC KVM_REG_PPC_TM_VSR0 128 2461 ... 2462 PPC KVM_REG_PPC_TM_VSR63 128 2463 PPC KVM_REG_PPC_TM_CR 64 2464 PPC KVM_REG_PPC_TM_LR 64 2465 PPC KVM_REG_PPC_TM_CTR 64 2466 PPC KVM_REG_PPC_TM_FPSCR 64 2467 PPC KVM_REG_PPC_TM_AMR 64 2468 PPC KVM_REG_PPC_TM_PPR 64 2469 PPC KVM_REG_PPC_TM_VRSAVE 64 2470 PPC KVM_REG_PPC_TM_VSCR 32 2471 PPC KVM_REG_PPC_TM_DSCR 64 2472 PPC KVM_REG_PPC_TM_TAR 64 2473 PPC KVM_REG_PPC_TM_XER 64 2474 2475 MIPS KVM_REG_MIPS_R0 64 2476 ... 2477 MIPS KVM_REG_MIPS_R31 64 2478 MIPS KVM_REG_MIPS_HI 64 2479 MIPS KVM_REG_MIPS_LO 64 2480 MIPS KVM_REG_MIPS_PC 64 2481 MIPS KVM_REG_MIPS_CP0_INDEX 32 2482 MIPS KVM_REG_MIPS_CP0_ENTRYLO0 64 2483 MIPS KVM_REG_MIPS_CP0_ENTRYLO1 64 2484 MIPS KVM_REG_MIPS_CP0_CONTEXT 64 2485 MIPS KVM_REG_MIPS_CP0_CONTEXTCONFIG 32 2486 MIPS KVM_REG_MIPS_CP0_USERLOCAL 64 2487 MIPS KVM_REG_MIPS_CP0_XCONTEXTCONFIG 64 2488 MIPS KVM_REG_MIPS_CP0_PAGEMASK 32 2489 MIPS KVM_REG_MIPS_CP0_PAGEGRAIN 32 2490 MIPS KVM_REG_MIPS_CP0_SEGCTL0 64 2491 MIPS KVM_REG_MIPS_CP0_SEGCTL1 64 2492 MIPS KVM_REG_MIPS_CP0_SEGCTL2 64 2493 MIPS KVM_REG_MIPS_CP0_PWBASE 64 2494 MIPS KVM_REG_MIPS_CP0_PWFIELD 64 2495 MIPS KVM_REG_MIPS_CP0_PWSIZE 64 2496 MIPS KVM_REG_MIPS_CP0_WIRED 32 2497 MIPS KVM_REG_MIPS_CP0_PWCTL 32 2498 MIPS KVM_REG_MIPS_CP0_HWRENA 32 2499 MIPS KVM_REG_MIPS_CP0_BADVADDR 64 2500 MIPS KVM_REG_MIPS_CP0_BADINSTR 32 2501 MIPS KVM_REG_MIPS_CP0_BADINSTRP 32 2502 MIPS KVM_REG_MIPS_CP0_COUNT 32 2503 MIPS KVM_REG_MIPS_CP0_ENTRYHI 64 2504 MIPS KVM_REG_MIPS_CP0_COMPARE 32 2505 MIPS KVM_REG_MIPS_CP0_STATUS 32 2506 MIPS KVM_REG_MIPS_CP0_INTCTL 32 2507 MIPS KVM_REG_MIPS_CP0_CAUSE 32 2508 MIPS KVM_REG_MIPS_CP0_EPC 64 2509 MIPS KVM_REG_MIPS_CP0_PRID 32 2510 MIPS KVM_REG_MIPS_CP0_EBASE 64 2511 MIPS KVM_REG_MIPS_CP0_CONFIG 32 2512 MIPS KVM_REG_MIPS_CP0_CONFIG1 32 2513 MIPS KVM_REG_MIPS_CP0_CONFIG2 32 2514 MIPS KVM_REG_MIPS_CP0_CONFIG3 32 2515 MIPS KVM_REG_MIPS_CP0_CONFIG4 32 2516 MIPS KVM_REG_MIPS_CP0_CONFIG5 32 2517 MIPS KVM_REG_MIPS_CP0_CONFIG7 32 2518 MIPS KVM_REG_MIPS_CP0_XCONTEXT 64 2519 MIPS KVM_REG_MIPS_CP0_ERROREPC 64 2520 MIPS KVM_REG_MIPS_CP0_KSCRATCH1 64 2521 MIPS KVM_REG_MIPS_CP0_KSCRATCH2 64 2522 MIPS KVM_REG_MIPS_CP0_KSCRATCH3 64 2523 MIPS KVM_REG_MIPS_CP0_KSCRATCH4 64 2524 MIPS KVM_REG_MIPS_CP0_KSCRATCH5 64 2525 MIPS KVM_REG_MIPS_CP0_KSCRATCH6 64 2526 MIPS KVM_REG_MIPS_CP0_MAAR(0..63) 64 2527 MIPS KVM_REG_MIPS_COUNT_CTL 64 2528 MIPS KVM_REG_MIPS_COUNT_RESUME 64 2529 MIPS KVM_REG_MIPS_COUNT_HZ 64 2530 MIPS KVM_REG_MIPS_FPR_32(0..31) 32 2531 MIPS KVM_REG_MIPS_FPR_64(0..31) 64 2532 MIPS KVM_REG_MIPS_VEC_128(0..31) 128 2533 MIPS KVM_REG_MIPS_FCR_IR 32 2534 MIPS KVM_REG_MIPS_FCR_CSR 32 2535 MIPS KVM_REG_MIPS_MSA_IR 32 2536 MIPS KVM_REG_MIPS_MSA_CSR 32 2537 ======= =============================== ============ 2538 2539ARM registers are mapped using the lower 32 bits. The upper 16 of that 2540is the register group type, or coprocessor number: 2541 2542ARM core registers have the following id bit patterns:: 2543 2544 0x4020 0000 0010 <index into the kvm_regs struct:16> 2545 2546ARM 32-bit CP15 registers have the following id bit patterns:: 2547 2548 0x4020 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3> 2549 2550ARM 64-bit CP15 registers have the following id bit patterns:: 2551 2552 0x4030 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3> 2553 2554ARM CCSIDR registers are demultiplexed by CSSELR value:: 2555 2556 0x4020 0000 0011 00 <csselr:8> 2557 2558ARM 32-bit VFP control registers have the following id bit patterns:: 2559 2560 0x4020 0000 0012 1 <regno:12> 2561 2562ARM 64-bit FP registers have the following id bit patterns:: 2563 2564 0x4030 0000 0012 0 <regno:12> 2565 2566ARM firmware pseudo-registers have the following bit pattern:: 2567 2568 0x4030 0000 0014 <regno:16> 2569 2570 2571arm64 registers are mapped using the lower 32 bits. The upper 16 of 2572that is the register group type, or coprocessor number: 2573 2574arm64 core/FP-SIMD registers have the following id bit patterns. Note 2575that the size of the access is variable, as the kvm_regs structure 2576contains elements ranging from 32 to 128 bits. The index is a 32bit 2577value in the kvm_regs structure seen as a 32bit array:: 2578 2579 0x60x0 0000 0010 <index into the kvm_regs struct:16> 2580 2581Specifically: 2582 2583======================= ========= ===== ======================================= 2584 Encoding Register Bits kvm_regs member 2585======================= ========= ===== ======================================= 2586 0x6030 0000 0010 0000 X0 64 regs.regs[0] 2587 0x6030 0000 0010 0002 X1 64 regs.regs[1] 2588 ... 2589 0x6030 0000 0010 003c X30 64 regs.regs[30] 2590 0x6030 0000 0010 003e SP 64 regs.sp 2591 0x6030 0000 0010 0040 PC 64 regs.pc 2592 0x6030 0000 0010 0042 PSTATE 64 regs.pstate 2593 0x6030 0000 0010 0044 SP_EL1 64 sp_el1 2594 0x6030 0000 0010 0046 ELR_EL1 64 elr_el1 2595 0x6030 0000 0010 0048 SPSR_EL1 64 spsr[KVM_SPSR_EL1] (alias SPSR_SVC) 2596 0x6030 0000 0010 004a SPSR_ABT 64 spsr[KVM_SPSR_ABT] 2597 0x6030 0000 0010 004c SPSR_UND 64 spsr[KVM_SPSR_UND] 2598 0x6030 0000 0010 004e SPSR_IRQ 64 spsr[KVM_SPSR_IRQ] 2599 0x6030 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ] 2600 0x6040 0000 0010 0054 V0 128 fp_regs.vregs[0] [1]_ 2601 0x6040 0000 0010 0058 V1 128 fp_regs.vregs[1] [1]_ 2602 ... 2603 0x6040 0000 0010 00d0 V31 128 fp_regs.vregs[31] [1]_ 2604 0x6020 0000 0010 00d4 FPSR 32 fp_regs.fpsr 2605 0x6020 0000 0010 00d5 FPCR 32 fp_regs.fpcr 2606======================= ========= ===== ======================================= 2607 2608.. [1] These encodings are not accepted for SVE-enabled vcpus. See 2609 :ref:`KVM_ARM_VCPU_INIT`. 2610 2611 The equivalent register content can be accessed via bits [127:0] of 2612 the corresponding SVE Zn registers instead for vcpus that have SVE 2613 enabled (see below). 2614 2615arm64 CCSIDR registers are demultiplexed by CSSELR value:: 2616 2617 0x6020 0000 0011 00 <csselr:8> 2618 2619arm64 system registers have the following id bit patterns:: 2620 2621 0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3> 2622 2623.. warning:: 2624 2625 Two system register IDs do not follow the specified pattern. These 2626 are KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT, which map to 2627 system registers CNTV_CVAL_EL0 and CNTVCT_EL0 respectively. These 2628 two had their values accidentally swapped, which means TIMER_CVAL is 2629 derived from the register encoding for CNTVCT_EL0 and TIMER_CNT is 2630 derived from the register encoding for CNTV_CVAL_EL0. As this is 2631 API, it must remain this way. 2632 2633arm64 firmware pseudo-registers have the following bit pattern:: 2634 2635 0x6030 0000 0014 <regno:16> 2636 2637arm64 SVE registers have the following bit patterns:: 2638 2639 0x6080 0000 0015 00 <n:5> <slice:5> Zn bits[2048*slice + 2047 : 2048*slice] 2640 0x6050 0000 0015 04 <n:4> <slice:5> Pn bits[256*slice + 255 : 256*slice] 2641 0x6050 0000 0015 060 <slice:5> FFR bits[256*slice + 255 : 256*slice] 2642 0x6060 0000 0015 ffff KVM_REG_ARM64_SVE_VLS pseudo-register 2643 2644Access to register IDs where 2048 * slice >= 128 * max_vq will fail with 2645ENOENT. max_vq is the vcpu's maximum supported vector length in 128-bit 2646quadwords: see [2]_ below. 2647 2648These registers are only accessible on vcpus for which SVE is enabled. 2649See KVM_ARM_VCPU_INIT for details. 2650 2651In addition, except for KVM_REG_ARM64_SVE_VLS, these registers are not 2652accessible until the vcpu's SVE configuration has been finalized 2653using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE). See KVM_ARM_VCPU_INIT 2654and KVM_ARM_VCPU_FINALIZE for more information about this procedure. 2655 2656KVM_REG_ARM64_SVE_VLS is a pseudo-register that allows the set of vector 2657lengths supported by the vcpu to be discovered and configured by 2658userspace. When transferred to or from user memory via KVM_GET_ONE_REG 2659or KVM_SET_ONE_REG, the value of this register is of type 2660__u64[KVM_ARM64_SVE_VLS_WORDS], and encodes the set of vector lengths as 2661follows:: 2662 2663 __u64 vector_lengths[KVM_ARM64_SVE_VLS_WORDS]; 2664 2665 if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX && 2666 ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >> 2667 ((vq - KVM_ARM64_SVE_VQ_MIN) % 64)) & 1)) 2668 /* Vector length vq * 16 bytes supported */ 2669 else 2670 /* Vector length vq * 16 bytes not supported */ 2671 2672.. [2] The maximum value vq for which the above condition is true is 2673 max_vq. This is the maximum vector length available to the guest on 2674 this vcpu, and determines which register slices are visible through 2675 this ioctl interface. 2676 2677(See Documentation/arch/arm64/sve.rst for an explanation of the "vq" 2678nomenclature.) 2679 2680KVM_REG_ARM64_SVE_VLS is only accessible after KVM_ARM_VCPU_INIT. 2681KVM_ARM_VCPU_INIT initialises it to the best set of vector lengths that 2682the host supports. 2683 2684Userspace may subsequently modify it if desired until the vcpu's SVE 2685configuration is finalized using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE). 2686 2687Apart from simply removing all vector lengths from the host set that 2688exceed some value, support for arbitrarily chosen sets of vector lengths 2689is hardware-dependent and may not be available. Attempting to configure 2690an invalid set of vector lengths via KVM_SET_ONE_REG will fail with 2691EINVAL. 2692 2693After the vcpu's SVE configuration is finalized, further attempts to 2694write this register will fail with EPERM. 2695 2696arm64 bitmap feature firmware pseudo-registers have the following bit pattern:: 2697 2698 0x6030 0000 0016 <regno:16> 2699 2700The bitmap feature firmware registers exposes the hypercall services that 2701are available for userspace to configure. The set bits corresponds to the 2702services that are available for the guests to access. By default, KVM 2703sets all the supported bits during VM initialization. The userspace can 2704discover the available services via KVM_GET_ONE_REG, and write back the 2705bitmap corresponding to the features that it wishes guests to see via 2706KVM_SET_ONE_REG. 2707 2708Note: These registers are immutable once any of the vCPUs of the VM has 2709run at least once. A KVM_SET_ONE_REG in such a scenario will return 2710a -EBUSY to userspace. 2711 2712(See Documentation/virt/kvm/arm/hypercalls.rst for more details.) 2713 2714 2715MIPS registers are mapped using the lower 32 bits. The upper 16 of that is 2716the register group type: 2717 2718MIPS core registers (see above) have the following id bit patterns:: 2719 2720 0x7030 0000 0000 <reg:16> 2721 2722MIPS CP0 registers (see KVM_REG_MIPS_CP0_* above) have the following id bit 2723patterns depending on whether they're 32-bit or 64-bit registers:: 2724 2725 0x7020 0000 0001 00 <reg:5> <sel:3> (32-bit) 2726 0x7030 0000 0001 00 <reg:5> <sel:3> (64-bit) 2727 2728Note: KVM_REG_MIPS_CP0_ENTRYLO0 and KVM_REG_MIPS_CP0_ENTRYLO1 are the MIPS64 2729versions of the EntryLo registers regardless of the word size of the host 2730hardware, host kernel, guest, and whether XPA is present in the guest, i.e. 2731with the RI and XI bits (if they exist) in bits 63 and 62 respectively, and 2732the PFNX field starting at bit 30. 2733 2734MIPS MAARs (see KVM_REG_MIPS_CP0_MAAR(*) above) have the following id bit 2735patterns:: 2736 2737 0x7030 0000 0001 01 <reg:8> 2738 2739MIPS KVM control registers (see above) have the following id bit patterns:: 2740 2741 0x7030 0000 0002 <reg:16> 2742 2743MIPS FPU registers (see KVM_REG_MIPS_FPR_{32,64}() above) have the following 2744id bit patterns depending on the size of the register being accessed. They are 2745always accessed according to the current guest FPU mode (Status.FR and 2746Config5.FRE), i.e. as the guest would see them, and they become unpredictable 2747if the guest FPU mode is changed. MIPS SIMD Architecture (MSA) vector 2748registers (see KVM_REG_MIPS_VEC_128() above) have similar patterns as they 2749overlap the FPU registers:: 2750 2751 0x7020 0000 0003 00 <0:3> <reg:5> (32-bit FPU registers) 2752 0x7030 0000 0003 00 <0:3> <reg:5> (64-bit FPU registers) 2753 0x7040 0000 0003 00 <0:3> <reg:5> (128-bit MSA vector registers) 2754 2755MIPS FPU control registers (see KVM_REG_MIPS_FCR_{IR,CSR} above) have the 2756following id bit patterns:: 2757 2758 0x7020 0000 0003 01 <0:3> <reg:5> 2759 2760MIPS MSA control registers (see KVM_REG_MIPS_MSA_{IR,CSR} above) have the 2761following id bit patterns:: 2762 2763 0x7020 0000 0003 02 <0:3> <reg:5> 2764 2765RISC-V registers are mapped using the lower 32 bits. The upper 8 bits of 2766that is the register group type. 2767 2768RISC-V config registers are meant for configuring a Guest VCPU and it has 2769the following id bit patterns:: 2770 2771 0x8020 0000 01 <index into the kvm_riscv_config struct:24> (32bit Host) 2772 0x8030 0000 01 <index into the kvm_riscv_config struct:24> (64bit Host) 2773 2774Following are the RISC-V config registers: 2775 2776======================= ========= ============================================= 2777 Encoding Register Description 2778======================= ========= ============================================= 2779 0x80x0 0000 0100 0000 isa ISA feature bitmap of Guest VCPU 2780======================= ========= ============================================= 2781 2782The isa config register can be read anytime but can only be written before 2783a Guest VCPU runs. It will have ISA feature bits matching underlying host 2784set by default. 2785 2786RISC-V core registers represent the general execution state of a Guest VCPU 2787and it has the following id bit patterns:: 2788 2789 0x8020 0000 02 <index into the kvm_riscv_core struct:24> (32bit Host) 2790 0x8030 0000 02 <index into the kvm_riscv_core struct:24> (64bit Host) 2791 2792Following are the RISC-V core registers: 2793 2794======================= ========= ============================================= 2795 Encoding Register Description 2796======================= ========= ============================================= 2797 0x80x0 0000 0200 0000 regs.pc Program counter 2798 0x80x0 0000 0200 0001 regs.ra Return address 2799 0x80x0 0000 0200 0002 regs.sp Stack pointer 2800 0x80x0 0000 0200 0003 regs.gp Global pointer 2801 0x80x0 0000 0200 0004 regs.tp Task pointer 2802 0x80x0 0000 0200 0005 regs.t0 Caller saved register 0 2803 0x80x0 0000 0200 0006 regs.t1 Caller saved register 1 2804 0x80x0 0000 0200 0007 regs.t2 Caller saved register 2 2805 0x80x0 0000 0200 0008 regs.s0 Callee saved register 0 2806 0x80x0 0000 0200 0009 regs.s1 Callee saved register 1 2807 0x80x0 0000 0200 000a regs.a0 Function argument (or return value) 0 2808 0x80x0 0000 0200 000b regs.a1 Function argument (or return value) 1 2809 0x80x0 0000 0200 000c regs.a2 Function argument 2 2810 0x80x0 0000 0200 000d regs.a3 Function argument 3 2811 0x80x0 0000 0200 000e regs.a4 Function argument 4 2812 0x80x0 0000 0200 000f regs.a5 Function argument 5 2813 0x80x0 0000 0200 0010 regs.a6 Function argument 6 2814 0x80x0 0000 0200 0011 regs.a7 Function argument 7 2815 0x80x0 0000 0200 0012 regs.s2 Callee saved register 2 2816 0x80x0 0000 0200 0013 regs.s3 Callee saved register 3 2817 0x80x0 0000 0200 0014 regs.s4 Callee saved register 4 2818 0x80x0 0000 0200 0015 regs.s5 Callee saved register 5 2819 0x80x0 0000 0200 0016 regs.s6 Callee saved register 6 2820 0x80x0 0000 0200 0017 regs.s7 Callee saved register 7 2821 0x80x0 0000 0200 0018 regs.s8 Callee saved register 8 2822 0x80x0 0000 0200 0019 regs.s9 Callee saved register 9 2823 0x80x0 0000 0200 001a regs.s10 Callee saved register 10 2824 0x80x0 0000 0200 001b regs.s11 Callee saved register 11 2825 0x80x0 0000 0200 001c regs.t3 Caller saved register 3 2826 0x80x0 0000 0200 001d regs.t4 Caller saved register 4 2827 0x80x0 0000 0200 001e regs.t5 Caller saved register 5 2828 0x80x0 0000 0200 001f regs.t6 Caller saved register 6 2829 0x80x0 0000 0200 0020 mode Privilege mode (1 = S-mode or 0 = U-mode) 2830======================= ========= ============================================= 2831 2832RISC-V csr registers represent the supervisor mode control/status registers 2833of a Guest VCPU and it has the following id bit patterns:: 2834 2835 0x8020 0000 03 <index into the kvm_riscv_csr struct:24> (32bit Host) 2836 0x8030 0000 03 <index into the kvm_riscv_csr struct:24> (64bit Host) 2837 2838Following are the RISC-V csr registers: 2839 2840======================= ========= ============================================= 2841 Encoding Register Description 2842======================= ========= ============================================= 2843 0x80x0 0000 0300 0000 sstatus Supervisor status 2844 0x80x0 0000 0300 0001 sie Supervisor interrupt enable 2845 0x80x0 0000 0300 0002 stvec Supervisor trap vector base 2846 0x80x0 0000 0300 0003 sscratch Supervisor scratch register 2847 0x80x0 0000 0300 0004 sepc Supervisor exception program counter 2848 0x80x0 0000 0300 0005 scause Supervisor trap cause 2849 0x80x0 0000 0300 0006 stval Supervisor bad address or instruction 2850 0x80x0 0000 0300 0007 sip Supervisor interrupt pending 2851 0x80x0 0000 0300 0008 satp Supervisor address translation and protection 2852======================= ========= ============================================= 2853 2854RISC-V timer registers represent the timer state of a Guest VCPU and it has 2855the following id bit patterns:: 2856 2857 0x8030 0000 04 <index into the kvm_riscv_timer struct:24> 2858 2859Following are the RISC-V timer registers: 2860 2861======================= ========= ============================================= 2862 Encoding Register Description 2863======================= ========= ============================================= 2864 0x8030 0000 0400 0000 frequency Time base frequency (read-only) 2865 0x8030 0000 0400 0001 time Time value visible to Guest 2866 0x8030 0000 0400 0002 compare Time compare programmed by Guest 2867 0x8030 0000 0400 0003 state Time compare state (1 = ON or 0 = OFF) 2868======================= ========= ============================================= 2869 2870RISC-V F-extension registers represent the single precision floating point 2871state of a Guest VCPU and it has the following id bit patterns:: 2872 2873 0x8020 0000 05 <index into the __riscv_f_ext_state struct:24> 2874 2875Following are the RISC-V F-extension registers: 2876 2877======================= ========= ============================================= 2878 Encoding Register Description 2879======================= ========= ============================================= 2880 0x8020 0000 0500 0000 f[0] Floating point register 0 2881 ... 2882 0x8020 0000 0500 001f f[31] Floating point register 31 2883 0x8020 0000 0500 0020 fcsr Floating point control and status register 2884======================= ========= ============================================= 2885 2886RISC-V D-extension registers represent the double precision floating point 2887state of a Guest VCPU and it has the following id bit patterns:: 2888 2889 0x8020 0000 06 <index into the __riscv_d_ext_state struct:24> (fcsr) 2890 0x8030 0000 06 <index into the __riscv_d_ext_state struct:24> (non-fcsr) 2891 2892Following are the RISC-V D-extension registers: 2893 2894======================= ========= ============================================= 2895 Encoding Register Description 2896======================= ========= ============================================= 2897 0x8030 0000 0600 0000 f[0] Floating point register 0 2898 ... 2899 0x8030 0000 0600 001f f[31] Floating point register 31 2900 0x8020 0000 0600 0020 fcsr Floating point control and status register 2901======================= ========= ============================================= 2902 2903LoongArch registers are mapped using the lower 32 bits. The upper 16 bits of 2904that is the register group type. 2905 2906LoongArch csr registers are used to control guest cpu or get status of guest 2907cpu, and they have the following id bit patterns:: 2908 2909 0x9030 0000 0001 00 <reg:5> <sel:3> (64-bit) 2910 2911LoongArch KVM control registers are used to implement some new defined functions 2912such as set vcpu counter or reset vcpu, and they have the following id bit patterns:: 2913 2914 0x9030 0000 0002 <reg:16> 2915 2916x86 MSR registers have the following id bit patterns:: 2917 0x2030 0002 <msr number:32> 2918 2919Following are the KVM-defined registers for x86: 2920 2921======================= ========= ============================================= 2922 Encoding Register Description 2923======================= ========= ============================================= 2924 0x2030 0003 0000 0000 SSP Shadow Stack Pointer 2925======================= ========= ============================================= 2926 29274.69 KVM_GET_ONE_REG 2928-------------------- 2929 2930:Capability: KVM_CAP_ONE_REG 2931:Architectures: all 2932:Type: vcpu ioctl 2933:Parameters: struct kvm_one_reg (in and out) 2934:Returns: 0 on success, negative value on failure 2935 2936Errors include: 2937 2938 ======== ============================================================ 2939 ENOENT no such register 2940 EINVAL invalid register ID, or no such register or used with VMs in 2941 protected virtualization mode on s390 2942 EPERM (arm64) register access not allowed before vcpu finalization 2943 ======== ============================================================ 2944 2945(These error codes are indicative only: do not rely on a specific error 2946code being returned in a specific situation.) 2947 2948This ioctl allows to receive the value of a single register implemented 2949in a vcpu. The register to read is indicated by the "id" field of the 2950kvm_one_reg struct passed in. On success, the register value can be found 2951at the memory location pointed to by "addr". 2952 2953The list of registers accessible using this interface is identical to the 2954list in 4.68. 2955 2956 29574.70 KVM_KVMCLOCK_CTRL 2958---------------------- 2959 2960:Capability: KVM_CAP_KVMCLOCK_CTRL 2961:Architectures: Any that implement pvclocks (currently x86 only) 2962:Type: vcpu ioctl 2963:Parameters: None 2964:Returns: 0 on success, -1 on error 2965 2966This ioctl sets a flag accessible to the guest indicating that the specified 2967vCPU has been paused by the host userspace. 2968 2969The host will set a flag in the pvclock structure that is checked from the 2970soft lockup watchdog. The flag is part of the pvclock structure that is 2971shared between guest and host, specifically the second bit of the flags 2972field of the pvclock_vcpu_time_info structure. It will be set exclusively by 2973the host and read/cleared exclusively by the guest. The guest operation of 2974checking and clearing the flag must be an atomic operation so 2975load-link/store-conditional, or equivalent must be used. There are two cases 2976where the guest will clear the flag: when the soft lockup watchdog timer resets 2977itself or when a soft lockup is detected. This ioctl can be called any time 2978after pausing the vcpu, but before it is resumed. 2979 2980 29814.71 KVM_SIGNAL_MSI 2982------------------- 2983 2984:Capability: KVM_CAP_SIGNAL_MSI 2985:Architectures: x86 arm64 2986:Type: vm ioctl 2987:Parameters: struct kvm_msi (in) 2988:Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error 2989 2990Directly inject a MSI message. Only valid with in-kernel irqchip that handles 2991MSI messages. 2992 2993:: 2994 2995 struct kvm_msi { 2996 __u32 address_lo; 2997 __u32 address_hi; 2998 __u32 data; 2999 __u32 flags; 3000 __u32 devid; 3001 __u8 pad[12]; 3002 }; 3003 3004flags: 3005 KVM_MSI_VALID_DEVID: devid contains a valid value. The per-VM 3006 KVM_CAP_MSI_DEVID capability advertises the requirement to provide 3007 the device ID. If this capability is not available, userspace 3008 should never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail. 3009 3010If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier 3011for the device that wrote the MSI message. For PCI, this is usually a 3012BDF identifier in the lower 16 bits. 3013 3014On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS 3015feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled, 3016address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of 3017address_hi must be zero. 3018 3019 30204.71 KVM_CREATE_PIT2 3021-------------------- 3022 3023:Capability: KVM_CAP_PIT2 3024:Architectures: x86 3025:Type: vm ioctl 3026:Parameters: struct kvm_pit_config (in) 3027:Returns: 0 on success, -1 on error 3028 3029Creates an in-kernel device model for the i8254 PIT. This call is only valid 3030after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following 3031parameters have to be passed:: 3032 3033 struct kvm_pit_config { 3034 __u32 flags; 3035 __u32 pad[15]; 3036 }; 3037 3038Valid flags are:: 3039 3040 #define KVM_PIT_SPEAKER_DUMMY 1 /* emulate speaker port stub */ 3041 3042PIT timer interrupts may use a per-VM kernel thread for injection. If it 3043exists, this thread will have a name of the following pattern:: 3044 3045 kvm-pit/<owner-process-pid> 3046 3047When running a guest with elevated priorities, the scheduling parameters of 3048this thread may have to be adjusted accordingly. 3049 3050This IOCTL replaces the obsolete KVM_CREATE_PIT. 3051 3052 30534.72 KVM_GET_PIT2 3054----------------- 3055 3056:Capability: KVM_CAP_PIT_STATE2 3057:Architectures: x86 3058:Type: vm ioctl 3059:Parameters: struct kvm_pit_state2 (out) 3060:Returns: 0 on success, -1 on error 3061 3062Retrieves the state of the in-kernel PIT model. Only valid after 3063KVM_CREATE_PIT2. The state is returned in the following structure:: 3064 3065 struct kvm_pit_state2 { 3066 struct kvm_pit_channel_state channels[3]; 3067 __u32 flags; 3068 __u32 reserved[9]; 3069 }; 3070 3071Valid flags are:: 3072 3073 /* disable PIT in HPET legacy mode */ 3074 #define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001 3075 /* speaker port data bit enabled */ 3076 #define KVM_PIT_FLAGS_SPEAKER_DATA_ON 0x00000002 3077 3078This IOCTL replaces the obsolete KVM_GET_PIT. 3079 3080 30814.73 KVM_SET_PIT2 3082----------------- 3083 3084:Capability: KVM_CAP_PIT_STATE2 3085:Architectures: x86 3086:Type: vm ioctl 3087:Parameters: struct kvm_pit_state2 (in) 3088:Returns: 0 on success, -1 on error 3089 3090Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2. 3091See KVM_GET_PIT2 for details on struct kvm_pit_state2. 3092 3093.. Tip:: 3094 ``KVM_SET_PIT2`` strictly adheres to the spec of Intel 8254 PIT. For example, 3095 a ``count`` value of 0 in ``struct kvm_pit_channel_state`` is interpreted as 3096 65536, which is the maximum count value. Refer to `Intel 8254 programmable 3097 interval timer <https://www.scs.stanford.edu/10wi-cs140/pintos/specs/8254.pdf>`_. 3098 3099This IOCTL replaces the obsolete KVM_SET_PIT. 3100 3101 31024.74 KVM_PPC_GET_SMMU_INFO 3103-------------------------- 3104 3105:Capability: KVM_CAP_PPC_GET_SMMU_INFO 3106:Architectures: powerpc 3107:Type: vm ioctl 3108:Parameters: None 3109:Returns: 0 on success, -1 on error 3110 3111This populates and returns a structure describing the features of 3112the "Server" class MMU emulation supported by KVM. 3113This can in turn be used by userspace to generate the appropriate 3114device-tree properties for the guest operating system. 3115 3116The structure contains some global information, followed by an 3117array of supported segment page sizes:: 3118 3119 struct kvm_ppc_smmu_info { 3120 __u64 flags; 3121 __u32 slb_size; 3122 __u32 pad; 3123 struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; 3124 }; 3125 3126The supported flags are: 3127 3128 - KVM_PPC_PAGE_SIZES_REAL: 3129 When that flag is set, guest page sizes must "fit" the backing 3130 store page sizes. When not set, any page size in the list can 3131 be used regardless of how they are backed by userspace. 3132 3133 - KVM_PPC_1T_SEGMENTS 3134 The emulated MMU supports 1T segments in addition to the 3135 standard 256M ones. 3136 3137 - KVM_PPC_NO_HASH 3138 This flag indicates that HPT guests are not supported by KVM, 3139 thus all guests must use radix MMU mode. 3140 3141The "slb_size" field indicates how many SLB entries are supported 3142 3143The "sps" array contains 8 entries indicating the supported base 3144page sizes for a segment in increasing order. Each entry is defined 3145as follow:: 3146 3147 struct kvm_ppc_one_seg_page_size { 3148 __u32 page_shift; /* Base page shift of segment (or 0) */ 3149 __u32 slb_enc; /* SLB encoding for BookS */ 3150 struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; 3151 }; 3152 3153An entry with a "page_shift" of 0 is unused. Because the array is 3154organized in increasing order, a lookup can stop when encountering 3155such an entry. 3156 3157The "slb_enc" field provides the encoding to use in the SLB for the 3158page size. The bits are in positions such as the value can directly 3159be OR'ed into the "vsid" argument of the slbmte instruction. 3160 3161The "enc" array is a list which for each of those segment base page 3162size provides the list of supported actual page sizes (which can be 3163only larger or equal to the base page size), along with the 3164corresponding encoding in the hash PTE. Similarly, the array is 31658 entries sorted by increasing sizes and an entry with a "0" shift 3166is an empty entry and a terminator:: 3167 3168 struct kvm_ppc_one_page_size { 3169 __u32 page_shift; /* Page shift (or 0) */ 3170 __u32 pte_enc; /* Encoding in the HPTE (>>12) */ 3171 }; 3172 3173The "pte_enc" field provides a value that can OR'ed into the hash 3174PTE's RPN field (ie, it needs to be shifted left by 12 to OR it 3175into the hash PTE second double word). 3176 31774.75 KVM_IRQFD 3178-------------- 3179 3180:Capability: KVM_CAP_IRQFD 3181:Architectures: x86 s390 arm64 3182:Type: vm ioctl 3183:Parameters: struct kvm_irqfd (in) 3184:Returns: 0 on success, -1 on error 3185 3186Allows setting an eventfd to directly trigger a guest interrupt. 3187kvm_irqfd.fd specifies the file descriptor to use as the eventfd and 3188kvm_irqfd.gsi specifies the irqchip pin toggled by this event. When 3189an event is triggered on the eventfd, an interrupt is injected into 3190the guest using the specified gsi pin. The irqfd is removed using 3191the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd 3192and kvm_irqfd.gsi. 3193 3194With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD supports a de-assert and notify 3195mechanism allowing emulation of level-triggered, irqfd-based 3196interrupts. When KVM_IRQFD_FLAG_RESAMPLE is set the user must pass an 3197additional eventfd in the kvm_irqfd.resamplefd field. When operating 3198in resample mode, posting of an interrupt through kvm_irq.fd asserts 3199the specified gsi in the irqchip. When the irqchip is resampled, such 3200as from an EOI, the gsi is de-asserted and the user is notified via 3201kvm_irqfd.resamplefd. It is the user's responsibility to re-queue 3202the interrupt if the device making use of it still requires service. 3203Note that closing the resamplefd is not sufficient to disable the 3204irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment 3205and need not be specified with KVM_IRQFD_FLAG_DEASSIGN. 3206 3207On arm64, gsi routing being supported, the following can happen: 3208 3209- in case no routing entry is associated to this gsi, injection fails 3210- in case the gsi is associated to an irqchip routing entry, 3211 irqchip.pin + 32 corresponds to the injected SPI ID. 3212- in case the gsi is associated to an MSI routing entry, the MSI 3213 message and device ID are translated into an LPI (support restricted 3214 to GICv3 ITS in-kernel emulation). 3215 32164.76 KVM_PPC_ALLOCATE_HTAB 3217-------------------------- 3218 3219:Capability: KVM_CAP_PPC_ALLOC_HTAB 3220:Architectures: powerpc 3221:Type: vm ioctl 3222:Parameters: Pointer to u32 containing hash table order (in/out) 3223:Returns: 0 on success, -1 on error 3224 3225This requests the host kernel to allocate an MMU hash table for a 3226guest using the PAPR paravirtualization interface. This only does 3227anything if the kernel is configured to use the Book 3S HV style of 3228virtualization. Otherwise the capability doesn't exist and the ioctl 3229returns an ENOTTY error. The rest of this description assumes Book 3S 3230HV. 3231 3232There must be no vcpus running when this ioctl is called; if there 3233are, it will do nothing and return an EBUSY error. 3234 3235The parameter is a pointer to a 32-bit unsigned integer variable 3236containing the order (log base 2) of the desired size of the hash 3237table, which must be between 18 and 46. On successful return from the 3238ioctl, the value will not be changed by the kernel. 3239 3240If no hash table has been allocated when any vcpu is asked to run 3241(with the KVM_RUN ioctl), the host kernel will allocate a 3242default-sized hash table (16 MB). 3243 3244If this ioctl is called when a hash table has already been allocated, 3245with a different order from the existing hash table, the existing hash 3246table will be freed and a new one allocated. If this is ioctl is 3247called when a hash table has already been allocated of the same order 3248as specified, the kernel will clear out the existing hash table (zero 3249all HPTEs). In either case, if the guest is using the virtualized 3250real-mode area (VRMA) facility, the kernel will re-create the VMRA 3251HPTEs on the next KVM_RUN of any vcpu. 3252 32534.77 KVM_S390_INTERRUPT 3254----------------------- 3255 3256:Capability: basic 3257:Architectures: s390 3258:Type: vm ioctl, vcpu ioctl 3259:Parameters: struct kvm_s390_interrupt (in) 3260:Returns: 0 on success, -1 on error 3261 3262Allows to inject an interrupt to the guest. Interrupts can be floating 3263(vm ioctl) or per cpu (vcpu ioctl), depending on the interrupt type. 3264 3265Interrupt parameters are passed via kvm_s390_interrupt:: 3266 3267 struct kvm_s390_interrupt { 3268 __u32 type; 3269 __u32 parm; 3270 __u64 parm64; 3271 }; 3272 3273type can be one of the following: 3274 3275KVM_S390_SIGP_STOP (vcpu) 3276 - sigp stop; optional flags in parm 3277KVM_S390_PROGRAM_INT (vcpu) 3278 - program check; code in parm 3279KVM_S390_SIGP_SET_PREFIX (vcpu) 3280 - sigp set prefix; prefix address in parm 3281KVM_S390_RESTART (vcpu) 3282 - restart 3283KVM_S390_INT_CLOCK_COMP (vcpu) 3284 - clock comparator interrupt 3285KVM_S390_INT_CPU_TIMER (vcpu) 3286 - CPU timer interrupt 3287KVM_S390_INT_VIRTIO (vm) 3288 - virtio external interrupt; external interrupt 3289 parameters in parm and parm64 3290KVM_S390_INT_SERVICE (vm) 3291 - sclp external interrupt; sclp parameter in parm 3292KVM_S390_INT_EMERGENCY (vcpu) 3293 - sigp emergency; source cpu in parm 3294KVM_S390_INT_EXTERNAL_CALL (vcpu) 3295 - sigp external call; source cpu in parm 3296KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) 3297 - compound value to indicate an 3298 I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel); 3299 I/O interruption parameters in parm (subchannel) and parm64 (intparm, 3300 interruption subclass) 3301KVM_S390_MCHK (vm, vcpu) 3302 - machine check interrupt; cr 14 bits in parm, machine check interrupt 3303 code in parm64 (note that machine checks needing further payload are not 3304 supported by this ioctl) 3305 3306This is an asynchronous vcpu ioctl and can be invoked from any thread. 3307 33084.78 KVM_PPC_GET_HTAB_FD 3309------------------------ 3310 3311:Capability: KVM_CAP_PPC_HTAB_FD 3312:Architectures: powerpc 3313:Type: vm ioctl 3314:Parameters: Pointer to struct kvm_get_htab_fd (in) 3315:Returns: file descriptor number (>= 0) on success, -1 on error 3316 3317This returns a file descriptor that can be used either to read out the 3318entries in the guest's hashed page table (HPT), or to write entries to 3319initialize the HPT. The returned fd can only be written to if the 3320KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and 3321can only be read if that bit is clear. The argument struct looks like 3322this:: 3323 3324 /* For KVM_PPC_GET_HTAB_FD */ 3325 struct kvm_get_htab_fd { 3326 __u64 flags; 3327 __u64 start_index; 3328 __u64 reserved[2]; 3329 }; 3330 3331 /* Values for kvm_get_htab_fd.flags */ 3332 #define KVM_GET_HTAB_BOLTED_ONLY ((__u64)0x1) 3333 #define KVM_GET_HTAB_WRITE ((__u64)0x2) 3334 3335The 'start_index' field gives the index in the HPT of the entry at 3336which to start reading. It is ignored when writing. 3337 3338Reads on the fd will initially supply information about all 3339"interesting" HPT entries. Interesting entries are those with the 3340bolted bit set, if the KVM_GET_HTAB_BOLTED_ONLY bit is set, otherwise 3341all entries. When the end of the HPT is reached, the read() will 3342return. If read() is called again on the fd, it will start again from 3343the beginning of the HPT, but will only return HPT entries that have 3344changed since they were last read. 3345 3346Data read or written is structured as a header (8 bytes) followed by a 3347series of valid HPT entries (16 bytes) each. The header indicates how 3348many valid HPT entries there are and how many invalid entries follow 3349the valid entries. The invalid entries are not represented explicitly 3350in the stream. The header format is:: 3351 3352 struct kvm_get_htab_header { 3353 __u32 index; 3354 __u16 n_valid; 3355 __u16 n_invalid; 3356 }; 3357 3358Writes to the fd create HPT entries starting at the index given in the 3359header; first 'n_valid' valid entries with contents from the data 3360written, then 'n_invalid' invalid entries, invalidating any previously 3361valid entries found. 3362 33634.79 KVM_CREATE_DEVICE 3364---------------------- 3365 3366:Capability: KVM_CAP_DEVICE_CTRL 3367:Architectures: all 3368:Type: vm ioctl 3369:Parameters: struct kvm_create_device (in/out) 3370:Returns: 0 on success, -1 on error 3371 3372Errors: 3373 3374 ====== ======================================================= 3375 ENODEV The device type is unknown or unsupported 3376 EEXIST Device already created, and this type of device may not 3377 be instantiated multiple times 3378 ====== ======================================================= 3379 3380 Other error conditions may be defined by individual device types or 3381 have their standard meanings. 3382 3383Creates an emulated device in the kernel. The file descriptor returned 3384in fd can be used with KVM_SET/GET/HAS_DEVICE_ATTR. 3385 3386If the KVM_CREATE_DEVICE_TEST flag is set, only test whether the 3387device type is supported (not necessarily whether it can be created 3388in the current vm). 3389 3390Individual devices should not define flags. Attributes should be used 3391for specifying any behavior that is not implied by the device type 3392number. 3393 3394:: 3395 3396 struct kvm_create_device { 3397 __u32 type; /* in: KVM_DEV_TYPE_xxx */ 3398 __u32 fd; /* out: device handle */ 3399 __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */ 3400 }; 3401 34024.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR 3403-------------------------------------------- 3404 3405:Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, 3406 KVM_CAP_VCPU_ATTRIBUTES for vcpu device 3407 KVM_CAP_SYS_ATTRIBUTES for system (/dev/kvm) device (no set) 3408:Architectures: x86, arm64, s390 3409:Type: device ioctl, vm ioctl, vcpu ioctl 3410:Parameters: struct kvm_device_attr 3411:Returns: 0 on success, -1 on error 3412 3413Errors: 3414 3415 ===== ============================================================= 3416 ENXIO The group or attribute is unknown/unsupported for this device 3417 or hardware support is missing. 3418 EPERM The attribute cannot (currently) be accessed this way 3419 (e.g. read-only attribute, or attribute that only makes 3420 sense when the device is in a different state) 3421 ===== ============================================================= 3422 3423 Other error conditions may be defined by individual device types. 3424 3425Gets/sets a specified piece of device configuration and/or state. The 3426semantics are device-specific. See individual device documentation in 3427the "devices" directory. As with ONE_REG, the size of the data 3428transferred is defined by the particular attribute. 3429 3430:: 3431 3432 struct kvm_device_attr { 3433 __u32 flags; /* no flags currently defined */ 3434 __u32 group; /* device-defined */ 3435 __u64 attr; /* group-defined */ 3436 __u64 addr; /* userspace address of attr data */ 3437 }; 3438 34394.81 KVM_HAS_DEVICE_ATTR 3440------------------------ 3441 3442:Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, 3443 KVM_CAP_VCPU_ATTRIBUTES for vcpu device 3444 KVM_CAP_SYS_ATTRIBUTES for system (/dev/kvm) device 3445:Type: device ioctl, vm ioctl, vcpu ioctl 3446:Parameters: struct kvm_device_attr 3447:Returns: 0 on success, -1 on error 3448 3449Errors: 3450 3451 ===== ============================================================= 3452 ENXIO The group or attribute is unknown/unsupported for this device 3453 or hardware support is missing. 3454 ===== ============================================================= 3455 3456Tests whether a device supports a particular attribute. A successful 3457return indicates the attribute is implemented. It does not necessarily 3458indicate that the attribute can be read or written in the device's 3459current state. "addr" is ignored. 3460 3461.. _KVM_ARM_VCPU_INIT: 3462 34634.82 KVM_ARM_VCPU_INIT 3464---------------------- 3465 3466:Capability: basic 3467:Architectures: arm64 3468:Type: vcpu ioctl 3469:Parameters: struct kvm_vcpu_init (in) 3470:Returns: 0 on success; -1 on error 3471 3472Errors: 3473 3474 ====== ================================================================= 3475 EINVAL the target is unknown, or the combination of features is invalid. 3476 ENOENT a features bit specified is unknown. 3477 ====== ================================================================= 3478 3479This tells KVM what type of CPU to present to the guest, and what 3480optional features it should have. This will cause a reset of the cpu 3481registers to their initial values. If this is not called, KVM_RUN will 3482return ENOEXEC for that vcpu. 3483 3484The initial values are defined as: 3485 - Processor state: 3486 * AArch64: EL1h, D, A, I and F bits set. All other bits 3487 are cleared. 3488 * AArch32: SVC, A, I and F bits set. All other bits are 3489 cleared. 3490 - General Purpose registers, including PC and SP: set to 0 3491 - FPSIMD/NEON registers: set to 0 3492 - SVE registers: set to 0 3493 - System registers: Reset to their architecturally defined 3494 values as for a warm reset to EL1 (resp. SVC) or EL2 (in the 3495 case of EL2 being enabled). 3496 3497Note that because some registers reflect machine topology, all vcpus 3498should be created before this ioctl is invoked. 3499 3500Userspace can call this function multiple times for a given vcpu, including 3501after the vcpu has been run. This will reset the vcpu to its initial 3502state. All calls to this function after the initial call must use the same 3503target and same set of feature flags, otherwise EINVAL will be returned. 3504 3505Possible features: 3506 3507 - KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state. 3508 Depends on KVM_CAP_ARM_PSCI. If not set, the CPU will be powered on 3509 and execute guest code when KVM_RUN is called. 3510 - KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode. 3511 Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only). 3512 - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 (or a future revision 3513 backward compatible with v0.2) for the CPU. 3514 Depends on KVM_CAP_ARM_PSCI_0_2. 3515 - KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU. 3516 Depends on KVM_CAP_ARM_PMU_V3. 3517 3518 - KVM_ARM_VCPU_PTRAUTH_ADDRESS: Enables Address Pointer authentication 3519 for arm64 only. 3520 Depends on KVM_CAP_ARM_PTRAUTH_ADDRESS. 3521 If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are 3522 both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and 3523 KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be 3524 requested. 3525 3526 - KVM_ARM_VCPU_PTRAUTH_GENERIC: Enables Generic Pointer authentication 3527 for arm64 only. 3528 Depends on KVM_CAP_ARM_PTRAUTH_GENERIC. 3529 If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are 3530 both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and 3531 KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be 3532 requested. 3533 3534 - KVM_ARM_VCPU_SVE: Enables SVE for the CPU (arm64 only). 3535 Depends on KVM_CAP_ARM_SVE. 3536 Requires KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE): 3537 3538 * After KVM_ARM_VCPU_INIT: 3539 3540 - KVM_REG_ARM64_SVE_VLS may be read using KVM_GET_ONE_REG: the 3541 initial value of this pseudo-register indicates the best set of 3542 vector lengths possible for a vcpu on this host. 3543 3544 * Before KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE): 3545 3546 - KVM_RUN and KVM_GET_REG_LIST are not available; 3547 3548 - KVM_GET_ONE_REG and KVM_SET_ONE_REG cannot be used to access 3549 the scalable architectural SVE registers 3550 KVM_REG_ARM64_SVE_ZREG(), KVM_REG_ARM64_SVE_PREG() or 3551 KVM_REG_ARM64_SVE_FFR; 3552 3553 - KVM_REG_ARM64_SVE_VLS may optionally be written using 3554 KVM_SET_ONE_REG, to modify the set of vector lengths available 3555 for the vcpu. 3556 3557 * After KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE): 3558 3559 - the KVM_REG_ARM64_SVE_VLS pseudo-register is immutable, and can 3560 no longer be written using KVM_SET_ONE_REG. 3561 3562 - KVM_ARM_VCPU_HAS_EL2: Enable Nested Virtualisation support, 3563 booting the guest from EL2 instead of EL1. 3564 Depends on KVM_CAP_ARM_EL2. 3565 The VM is running with HCR_EL2.E2H being RES1 (VHE) unless 3566 KVM_ARM_VCPU_HAS_EL2_E2H0 is also set. 3567 3568 - KVM_ARM_VCPU_HAS_EL2_E2H0: Restrict Nested Virtualisation 3569 support to HCR_EL2.E2H being RES0 (non-VHE). 3570 Depends on KVM_CAP_ARM_EL2_E2H0. 3571 KVM_ARM_VCPU_HAS_EL2 must also be set. 3572 35734.83 KVM_ARM_PREFERRED_TARGET 3574----------------------------- 3575 3576:Capability: basic 3577:Architectures: arm64 3578:Type: vm ioctl 3579:Parameters: struct kvm_vcpu_init (out) 3580:Returns: 0 on success; -1 on error 3581 3582Errors: 3583 3584 ====== ========================================== 3585 ENODEV no preferred target available for the host 3586 ====== ========================================== 3587 3588This queries KVM for preferred CPU target type which can be emulated 3589by KVM on underlying host. 3590 3591The ioctl returns struct kvm_vcpu_init instance containing information 3592about preferred CPU target type and recommended features for it. The 3593kvm_vcpu_init->features bitmap returned will have feature bits set if 3594the preferred target recommends setting these features, but this is 3595not mandatory. 3596 3597The information returned by this ioctl can be used to prepare an instance 3598of struct kvm_vcpu_init for KVM_ARM_VCPU_INIT ioctl which will result in 3599VCPU matching underlying host. 3600 3601 36024.84 KVM_GET_REG_LIST 3603--------------------- 3604 3605:Capability: basic 3606:Architectures: arm64, mips, riscv, x86 (if KVM_CAP_ONE_REG) 3607:Type: vcpu ioctl 3608:Parameters: struct kvm_reg_list (in/out) 3609:Returns: 0 on success; -1 on error 3610 3611Errors: 3612 3613 ===== ============================================================== 3614 E2BIG the reg index list is too big to fit in the array specified by 3615 the user (the number required will be written into n). 3616 ===== ============================================================== 3617 3618:: 3619 3620 struct kvm_reg_list { 3621 __u64 n; /* number of registers in reg[] */ 3622 __u64 reg[0]; 3623 }; 3624 3625This ioctl returns the guest registers that are supported for the 3626KVM_GET_ONE_REG/KVM_SET_ONE_REG calls. 3627 3628Note that s390 does not support KVM_GET_REG_LIST for historical reasons 3629(read: nobody cared). The set of registers in kernels 4.x and newer is: 3630 3631- KVM_REG_S390_TODPR 3632 3633- KVM_REG_S390_EPOCHDIFF 3634 3635- KVM_REG_S390_CPU_TIMER 3636 3637- KVM_REG_S390_CLOCK_COMP 3638 3639- KVM_REG_S390_PFTOKEN 3640 3641- KVM_REG_S390_PFCOMPARE 3642 3643- KVM_REG_S390_PFSELECT 3644 3645- KVM_REG_S390_PP 3646 3647- KVM_REG_S390_GBEA 3648 3649Note, for x86, all MSRs enumerated by KVM_GET_MSR_INDEX_LIST are supported as 3650type KVM_X86_REG_TYPE_MSR, but are NOT enumerated via KVM_GET_REG_LIST. 3651 36524.85 KVM_ARM_SET_DEVICE_ADDR (deprecated) 3653----------------------------------------- 3654 3655:Capability: KVM_CAP_ARM_SET_DEVICE_ADDR 3656:Architectures: arm64 3657:Type: vm ioctl 3658:Parameters: struct kvm_arm_device_address (in) 3659:Returns: 0 on success, -1 on error 3660 3661Errors: 3662 3663 ====== ============================================ 3664 ENODEV The device id is unknown 3665 ENXIO Device not supported on current system 3666 EEXIST Address already set 3667 E2BIG Address outside guest physical address space 3668 EBUSY Address overlaps with other device range 3669 ====== ============================================ 3670 3671:: 3672 3673 struct kvm_arm_device_addr { 3674 __u64 id; 3675 __u64 addr; 3676 }; 3677 3678Specify a device address in the guest's physical address space where guests 3679can access emulated or directly exposed devices, which the host kernel needs 3680to know about. The id field is an architecture specific identifier for a 3681specific device. 3682 3683arm64 divides the id field into two parts, a device id and an 3684address type id specific to the individual device:: 3685 3686 bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 | 3687 field: | 0x00000000 | device id | addr type id | 3688 3689arm64 currently only require this when using the in-kernel GIC 3690support for the hardware VGIC features, using KVM_ARM_DEVICE_VGIC_V2 3691as the device id. When setting the base address for the guest's 3692mapping of the VGIC virtual CPU and distributor interface, the ioctl 3693must be called after calling KVM_CREATE_IRQCHIP, but before calling 3694KVM_RUN on any of the VCPUs. Calling this ioctl twice for any of the 3695base addresses will return -EEXIST. 3696 3697Note, this IOCTL is deprecated and the more flexible SET/GET_DEVICE_ATTR API 3698should be used instead. 3699 3700 37014.86 KVM_PPC_RTAS_DEFINE_TOKEN 3702------------------------------ 3703 3704:Capability: KVM_CAP_PPC_RTAS 3705:Architectures: ppc 3706:Type: vm ioctl 3707:Parameters: struct kvm_rtas_token_args 3708:Returns: 0 on success, -1 on error 3709 3710Defines a token value for a RTAS (Run Time Abstraction Services) 3711service in order to allow it to be handled in the kernel. The 3712argument struct gives the name of the service, which must be the name 3713of a service that has a kernel-side implementation. If the token 3714value is non-zero, it will be associated with that service, and 3715subsequent RTAS calls by the guest specifying that token will be 3716handled by the kernel. If the token value is 0, then any token 3717associated with the service will be forgotten, and subsequent RTAS 3718calls by the guest for that service will be passed to userspace to be 3719handled. 3720 37214.87 KVM_SET_GUEST_DEBUG 3722------------------------ 3723 3724:Capability: KVM_CAP_SET_GUEST_DEBUG 3725:Architectures: x86, s390, ppc, arm64 3726:Type: vcpu ioctl 3727:Parameters: struct kvm_guest_debug (in) 3728:Returns: 0 on success; -1 on error 3729 3730:: 3731 3732 struct kvm_guest_debug { 3733 __u32 control; 3734 __u32 pad; 3735 struct kvm_guest_debug_arch arch; 3736 }; 3737 3738Set up the processor specific debug registers and configure vcpu for 3739handling guest debug events. There are two parts to the structure, the 3740first a control bitfield indicates the type of debug events to handle 3741when running. Common control bits are: 3742 3743 - KVM_GUESTDBG_ENABLE: guest debugging is enabled 3744 - KVM_GUESTDBG_SINGLESTEP: the next run should single-step 3745 3746The top 16 bits of the control field are architecture specific control 3747flags which can include the following: 3748 3749 - KVM_GUESTDBG_USE_SW_BP: using software breakpoints [x86, arm64] 3750 - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390] 3751 - KVM_GUESTDBG_USE_HW: using hardware debug events [arm64] 3752 - KVM_GUESTDBG_INJECT_DB: inject DB type exception [x86] 3753 - KVM_GUESTDBG_INJECT_BP: inject BP type exception [x86] 3754 - KVM_GUESTDBG_EXIT_PENDING: trigger an immediate guest exit [s390] 3755 - KVM_GUESTDBG_BLOCKIRQ: avoid injecting interrupts/NMI/SMI [x86] 3756 3757For example KVM_GUESTDBG_USE_SW_BP indicates that software breakpoints 3758are enabled in memory so we need to ensure breakpoint exceptions are 3759correctly trapped and the KVM run loop exits at the breakpoint and not 3760running off into the normal guest vector. For KVM_GUESTDBG_USE_HW_BP 3761we need to ensure the guest vCPUs architecture specific registers are 3762updated to the correct (supplied) values. 3763 3764The second part of the structure is architecture specific and 3765typically contains a set of debug registers. 3766 3767For arm64 the number of debug registers is implementation defined and 3768can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and 3769KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number 3770indicating the number of supported registers. 3771 3772For ppc, the KVM_CAP_PPC_GUEST_DEBUG_SSTEP capability indicates whether 3773the single-step debug event (KVM_GUESTDBG_SINGLESTEP) is supported. 3774 3775Also when supported, KVM_CAP_SET_GUEST_DEBUG2 capability indicates the 3776supported KVM_GUESTDBG_* bits in the control field. 3777 3778When debug events exit the main run loop with the reason 3779KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run 3780structure containing architecture specific debug information. 3781 37824.88 KVM_GET_EMULATED_CPUID 3783--------------------------- 3784 3785:Capability: KVM_CAP_EXT_EMUL_CPUID 3786:Architectures: x86 3787:Type: system ioctl 3788:Parameters: struct kvm_cpuid2 (in/out) 3789:Returns: 0 on success, -1 on error 3790 3791:: 3792 3793 struct kvm_cpuid2 { 3794 __u32 nent; 3795 __u32 flags; 3796 struct kvm_cpuid_entry2 entries[0]; 3797 }; 3798 3799The member 'flags' is used for passing flags from userspace. 3800 3801:: 3802 3803 #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) 3804 #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) /* deprecated */ 3805 #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) /* deprecated */ 3806 3807 struct kvm_cpuid_entry2 { 3808 __u32 function; 3809 __u32 index; 3810 __u32 flags; 3811 __u32 eax; 3812 __u32 ebx; 3813 __u32 ecx; 3814 __u32 edx; 3815 __u32 padding[3]; 3816 }; 3817 3818This ioctl returns x86 cpuid features which are emulated by 3819kvm.Userspace can use the information returned by this ioctl to query 3820which features are emulated by kvm instead of being present natively. 3821 3822Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2 3823structure with the 'nent' field indicating the number of entries in 3824the variable-size array 'entries'. If the number of entries is too low 3825to describe the cpu capabilities, an error (E2BIG) is returned. If the 3826number is too high, the 'nent' field is adjusted and an error (ENOMEM) 3827is returned. If the number is just right, the 'nent' field is adjusted 3828to the number of valid entries in the 'entries' array, which is then 3829filled. 3830 3831The entries returned are the set CPUID bits of the respective features 3832which kvm emulates, as returned by the CPUID instruction, with unknown 3833or unsupported feature bits cleared. 3834 3835Features like x2apic, for example, may not be present in the host cpu 3836but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be 3837emulated efficiently and thus not included here. 3838 3839The fields in each entry are defined as follows: 3840 3841 function: 3842 the eax value used to obtain the entry 3843 index: 3844 the ecx value used to obtain the entry (for entries that are 3845 affected by ecx) 3846 flags: 3847 an OR of zero or more of the following: 3848 3849 KVM_CPUID_FLAG_SIGNIFCANT_INDEX: 3850 if the index field is valid 3851 3852 eax, ebx, ecx, edx: 3853 3854 the values returned by the cpuid instruction for 3855 this function/index combination 3856 38574.89 KVM_S390_MEM_OP 3858-------------------- 3859 3860:Capability: KVM_CAP_S390_MEM_OP, KVM_CAP_S390_PROTECTED, KVM_CAP_S390_MEM_OP_EXTENSION 3861:Architectures: s390 3862:Type: vm ioctl, vcpu ioctl 3863:Parameters: struct kvm_s390_mem_op (in) 3864:Returns: = 0 on success, 3865 < 0 on generic error (e.g. -EFAULT or -ENOMEM), 3866 16 bit program exception code if the access causes such an exception 3867 3868Read or write data from/to the VM's memory. 3869The KVM_CAP_S390_MEM_OP_EXTENSION capability specifies what functionality is 3870supported. 3871 3872Parameters are specified via the following structure:: 3873 3874 struct kvm_s390_mem_op { 3875 __u64 gaddr; /* the guest address */ 3876 __u64 flags; /* flags */ 3877 __u32 size; /* amount of bytes */ 3878 __u32 op; /* type of operation */ 3879 __u64 buf; /* buffer in userspace */ 3880 union { 3881 struct { 3882 __u8 ar; /* the access register number */ 3883 __u8 key; /* access key, ignored if flag unset */ 3884 __u8 pad1[6]; /* ignored */ 3885 __u64 old_addr; /* ignored if flag unset */ 3886 }; 3887 __u32 sida_offset; /* offset into the sida */ 3888 __u8 reserved[32]; /* ignored */ 3889 }; 3890 }; 3891 3892The start address of the memory region has to be specified in the "gaddr" 3893field, and the length of the region in the "size" field (which must not 3894be 0). The maximum value for "size" can be obtained by checking the 3895KVM_CAP_S390_MEM_OP capability. "buf" is the buffer supplied by the 3896userspace application where the read data should be written to for 3897a read access, or where the data that should be written is stored for 3898a write access. The "reserved" field is meant for future extensions. 3899Reserved and unused values are ignored. Future extension that add members must 3900introduce new flags. 3901 3902The type of operation is specified in the "op" field. Flags modifying 3903their behavior can be set in the "flags" field. Undefined flag bits must 3904be set to 0. 3905 3906Possible operations are: 3907 * ``KVM_S390_MEMOP_LOGICAL_READ`` 3908 * ``KVM_S390_MEMOP_LOGICAL_WRITE`` 3909 * ``KVM_S390_MEMOP_ABSOLUTE_READ`` 3910 * ``KVM_S390_MEMOP_ABSOLUTE_WRITE`` 3911 * ``KVM_S390_MEMOP_SIDA_READ`` 3912 * ``KVM_S390_MEMOP_SIDA_WRITE`` 3913 * ``KVM_S390_MEMOP_ABSOLUTE_CMPXCHG`` 3914 3915Logical read/write: 3916^^^^^^^^^^^^^^^^^^^ 3917 3918Access logical memory, i.e. translate the given guest address to an absolute 3919address given the state of the VCPU and use the absolute address as target of 3920the access. "ar" designates the access register number to be used; the valid 3921range is 0..15. 3922Logical accesses are permitted for the VCPU ioctl only. 3923Logical accesses are permitted for non-protected guests only. 3924 3925Supported flags: 3926 * ``KVM_S390_MEMOP_F_CHECK_ONLY`` 3927 * ``KVM_S390_MEMOP_F_INJECT_EXCEPTION`` 3928 * ``KVM_S390_MEMOP_F_SKEY_PROTECTION`` 3929 3930The KVM_S390_MEMOP_F_CHECK_ONLY flag can be set to check whether the 3931corresponding memory access would cause an access exception; however, 3932no actual access to the data in memory at the destination is performed. 3933In this case, "buf" is unused and can be NULL. 3934 3935In case an access exception occurred during the access (or would occur 3936in case of KVM_S390_MEMOP_F_CHECK_ONLY), the ioctl returns a positive 3937error number indicating the type of exception. This exception is also 3938raised directly at the corresponding VCPU if the flag 3939KVM_S390_MEMOP_F_INJECT_EXCEPTION is set. 3940On protection exceptions, unless specified otherwise, the injected 3941translation-exception identifier (TEID) indicates suppression. 3942 3943If the KVM_S390_MEMOP_F_SKEY_PROTECTION flag is set, storage key 3944protection is also in effect and may cause exceptions if accesses are 3945prohibited given the access key designated by "key"; the valid range is 0..15. 3946KVM_S390_MEMOP_F_SKEY_PROTECTION is available if KVM_CAP_S390_MEM_OP_EXTENSION 3947is > 0. 3948Since the accessed memory may span multiple pages and those pages might have 3949different storage keys, it is possible that a protection exception occurs 3950after memory has been modified. In this case, if the exception is injected, 3951the TEID does not indicate suppression. 3952 3953Absolute read/write: 3954^^^^^^^^^^^^^^^^^^^^ 3955 3956Access absolute memory. This operation is intended to be used with the 3957KVM_S390_MEMOP_F_SKEY_PROTECTION flag, to allow accessing memory and performing 3958the checks required for storage key protection as one operation (as opposed to 3959user space getting the storage keys, performing the checks, and accessing 3960memory thereafter, which could lead to a delay between check and access). 3961Absolute accesses are permitted for the VM ioctl if KVM_CAP_S390_MEM_OP_EXTENSION 3962has the KVM_S390_MEMOP_EXTENSION_CAP_BASE bit set. 3963Currently absolute accesses are not permitted for VCPU ioctls. 3964Absolute accesses are permitted for non-protected guests only. 3965 3966Supported flags: 3967 * ``KVM_S390_MEMOP_F_CHECK_ONLY`` 3968 * ``KVM_S390_MEMOP_F_SKEY_PROTECTION`` 3969 3970The semantics of the flags common with logical accesses are as for logical 3971accesses. 3972 3973Absolute cmpxchg: 3974^^^^^^^^^^^^^^^^^ 3975 3976Perform cmpxchg on absolute guest memory. Intended for use with the 3977KVM_S390_MEMOP_F_SKEY_PROTECTION flag. 3978Instead of doing an unconditional write, the access occurs only if the target 3979location contains the value pointed to by "old_addr". 3980This is performed as an atomic cmpxchg with the length specified by the "size" 3981parameter. "size" must be a power of two up to and including 16. 3982If the exchange did not take place because the target value doesn't match the 3983old value, the value "old_addr" points to is replaced by the target value. 3984User space can tell if an exchange took place by checking if this replacement 3985occurred. The cmpxchg op is permitted for the VM ioctl if 3986KVM_CAP_S390_MEM_OP_EXTENSION has flag KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG set. 3987 3988Supported flags: 3989 * ``KVM_S390_MEMOP_F_SKEY_PROTECTION`` 3990 3991SIDA read/write: 3992^^^^^^^^^^^^^^^^ 3993 3994Access the secure instruction data area which contains memory operands necessary 3995for instruction emulation for protected guests. 3996SIDA accesses are available if the KVM_CAP_S390_PROTECTED capability is available. 3997SIDA accesses are permitted for the VCPU ioctl only. 3998SIDA accesses are permitted for protected guests only. 3999 4000No flags are supported. 4001 40024.90 KVM_S390_GET_SKEYS 4003----------------------- 4004 4005:Capability: KVM_CAP_S390_SKEYS 4006:Architectures: s390 4007:Type: vm ioctl 4008:Parameters: struct kvm_s390_skeys 4009:Returns: 0 on success, KVM_S390_GET_SKEYS_NONE if guest is not using storage 4010 keys, negative value on error 4011 4012This ioctl is used to get guest storage key values on the s390 4013architecture. The ioctl takes parameters via the kvm_s390_skeys struct:: 4014 4015 struct kvm_s390_skeys { 4016 __u64 start_gfn; 4017 __u64 count; 4018 __u64 skeydata_addr; 4019 __u32 flags; 4020 __u32 reserved[9]; 4021 }; 4022 4023The start_gfn field is the number of the first guest frame whose storage keys 4024you want to get. 4025 4026The count field is the number of consecutive frames (starting from start_gfn) 4027whose storage keys to get. The count field must be at least 1 and the maximum 4028allowed value is defined as KVM_S390_SKEYS_MAX. Values outside this range 4029will cause the ioctl to return -EINVAL. 4030 4031The skeydata_addr field is the address to a buffer large enough to hold count 4032bytes. This buffer will be filled with storage key data by the ioctl. 4033 40344.91 KVM_S390_SET_SKEYS 4035----------------------- 4036 4037:Capability: KVM_CAP_S390_SKEYS 4038:Architectures: s390 4039:Type: vm ioctl 4040:Parameters: struct kvm_s390_skeys 4041:Returns: 0 on success, negative value on error 4042 4043This ioctl is used to set guest storage key values on the s390 4044architecture. The ioctl takes parameters via the kvm_s390_skeys struct. 4045See section on KVM_S390_GET_SKEYS for struct definition. 4046 4047The start_gfn field is the number of the first guest frame whose storage keys 4048you want to set. 4049 4050The count field is the number of consecutive frames (starting from start_gfn) 4051whose storage keys to get. The count field must be at least 1 and the maximum 4052allowed value is defined as KVM_S390_SKEYS_MAX. Values outside this range 4053will cause the ioctl to return -EINVAL. 4054 4055The skeydata_addr field is the address to a buffer containing count bytes of 4056storage keys. Each byte in the buffer will be set as the storage key for a 4057single frame starting at start_gfn for count frames. 4058 4059Note: If any architecturally invalid key value is found in the given data then 4060the ioctl will return -EINVAL. 4061 40624.92 KVM_S390_IRQ 4063----------------- 4064 4065:Capability: KVM_CAP_S390_INJECT_IRQ 4066:Architectures: s390 4067:Type: vcpu ioctl 4068:Parameters: struct kvm_s390_irq (in) 4069:Returns: 0 on success, -1 on error 4070 4071Errors: 4072 4073 4074 ====== ================================================================= 4075 EINVAL interrupt type is invalid 4076 type is KVM_S390_SIGP_STOP and flag parameter is invalid value, 4077 type is KVM_S390_INT_EXTERNAL_CALL and code is bigger 4078 than the maximum of VCPUs 4079 EBUSY type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped, 4080 type is KVM_S390_SIGP_STOP and a stop irq is already pending, 4081 type is KVM_S390_INT_EXTERNAL_CALL and an external call interrupt 4082 is already pending 4083 ====== ================================================================= 4084 4085Allows to inject an interrupt to the guest. 4086 4087Using struct kvm_s390_irq as a parameter allows 4088to inject additional payload which is not 4089possible via KVM_S390_INTERRUPT. 4090 4091Interrupt parameters are passed via kvm_s390_irq:: 4092 4093 struct kvm_s390_irq { 4094 __u64 type; 4095 union { 4096 struct kvm_s390_io_info io; 4097 struct kvm_s390_ext_info ext; 4098 struct kvm_s390_pgm_info pgm; 4099 struct kvm_s390_emerg_info emerg; 4100 struct kvm_s390_extcall_info extcall; 4101 struct kvm_s390_prefix_info prefix; 4102 struct kvm_s390_stop_info stop; 4103 struct kvm_s390_mchk_info mchk; 4104 char reserved[64]; 4105 } u; 4106 }; 4107 4108type can be one of the following: 4109 4110- KVM_S390_SIGP_STOP - sigp stop; parameter in .stop 4111- KVM_S390_PROGRAM_INT - program check; parameters in .pgm 4112- KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix 4113- KVM_S390_RESTART - restart; no parameters 4114- KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters 4115- KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters 4116- KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg 4117- KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall 4118- KVM_S390_MCHK - machine check interrupt; parameters in .mchk 4119 4120This is an asynchronous vcpu ioctl and can be invoked from any thread. 4121 41224.94 KVM_S390_GET_IRQ_STATE 4123--------------------------- 4124 4125:Capability: KVM_CAP_S390_IRQ_STATE 4126:Architectures: s390 4127:Type: vcpu ioctl 4128:Parameters: struct kvm_s390_irq_state (out) 4129:Returns: >= number of bytes copied into buffer, 4130 -EINVAL if buffer size is 0, 4131 -ENOBUFS if buffer size is too small to fit all pending interrupts, 4132 -EFAULT if the buffer address was invalid 4133 4134This ioctl allows userspace to retrieve the complete state of all currently 4135pending interrupts in a single buffer. Use cases include migration 4136and introspection. The parameter structure contains the address of a 4137userspace buffer and its length:: 4138 4139 struct kvm_s390_irq_state { 4140 __u64 buf; 4141 __u32 flags; /* will stay unused for compatibility reasons */ 4142 __u32 len; 4143 __u32 reserved[4]; /* will stay unused for compatibility reasons */ 4144 }; 4145 4146Userspace passes in the above struct and for each pending interrupt a 4147struct kvm_s390_irq is copied to the provided buffer. 4148 4149The structure contains a flags and a reserved field for future extensions. As 4150the kernel never checked for flags == 0 and QEMU never pre-zeroed flags and 4151reserved, these fields can not be used in the future without breaking 4152compatibility. 4153 4154If -ENOBUFS is returned the buffer provided was too small and userspace 4155may retry with a bigger buffer. 4156 41574.95 KVM_S390_SET_IRQ_STATE 4158--------------------------- 4159 4160:Capability: KVM_CAP_S390_IRQ_STATE 4161:Architectures: s390 4162:Type: vcpu ioctl 4163:Parameters: struct kvm_s390_irq_state (in) 4164:Returns: 0 on success, 4165 -EFAULT if the buffer address was invalid, 4166 -EINVAL for an invalid buffer length (see below), 4167 -EBUSY if there were already interrupts pending, 4168 errors occurring when actually injecting the 4169 interrupt. See KVM_S390_IRQ. 4170 4171This ioctl allows userspace to set the complete state of all cpu-local 4172interrupts currently pending for the vcpu. It is intended for restoring 4173interrupt state after a migration. The input parameter is a userspace buffer 4174containing a struct kvm_s390_irq_state:: 4175 4176 struct kvm_s390_irq_state { 4177 __u64 buf; 4178 __u32 flags; /* will stay unused for compatibility reasons */ 4179 __u32 len; 4180 __u32 reserved[4]; /* will stay unused for compatibility reasons */ 4181 }; 4182 4183The restrictions for flags and reserved apply as well. 4184(see KVM_S390_GET_IRQ_STATE) 4185 4186The userspace memory referenced by buf contains a struct kvm_s390_irq 4187for each interrupt to be injected into the guest. 4188If one of the interrupts could not be injected for some reason the 4189ioctl aborts. 4190 4191len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0 4192and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq), 4193which is the maximum number of possibly pending cpu-local interrupts. 4194 41954.96 KVM_SMI 4196------------ 4197 4198:Capability: KVM_CAP_X86_SMM 4199:Architectures: x86 4200:Type: vcpu ioctl 4201:Parameters: none 4202:Returns: 0 on success, -1 on error 4203 4204Queues an SMI on the thread's vcpu. 4205 42064.97 KVM_X86_SET_MSR_FILTER 4207---------------------------- 4208 4209:Capability: KVM_CAP_X86_MSR_FILTER 4210:Architectures: x86 4211:Type: vm ioctl 4212:Parameters: struct kvm_msr_filter 4213:Returns: 0 on success, < 0 on error 4214 4215:: 4216 4217 struct kvm_msr_filter_range { 4218 #define KVM_MSR_FILTER_READ (1 << 0) 4219 #define KVM_MSR_FILTER_WRITE (1 << 1) 4220 __u32 flags; 4221 __u32 nmsrs; /* number of msrs in bitmap */ 4222 __u32 base; /* MSR index the bitmap starts at */ 4223 __u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */ 4224 }; 4225 4226 #define KVM_MSR_FILTER_MAX_RANGES 16 4227 struct kvm_msr_filter { 4228 #define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0) 4229 #define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0) 4230 __u32 flags; 4231 struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES]; 4232 }; 4233 4234flags values for ``struct kvm_msr_filter_range``: 4235 4236``KVM_MSR_FILTER_READ`` 4237 4238 Filter read accesses to MSRs using the given bitmap. A 0 in the bitmap 4239 indicates that read accesses should be denied, while a 1 indicates that 4240 a read for a particular MSR should be allowed regardless of the default 4241 filter action. 4242 4243``KVM_MSR_FILTER_WRITE`` 4244 4245 Filter write accesses to MSRs using the given bitmap. A 0 in the bitmap 4246 indicates that write accesses should be denied, while a 1 indicates that 4247 a write for a particular MSR should be allowed regardless of the default 4248 filter action. 4249 4250flags values for ``struct kvm_msr_filter``: 4251 4252``KVM_MSR_FILTER_DEFAULT_ALLOW`` 4253 4254 If no filter range matches an MSR index that is getting accessed, KVM will 4255 allow accesses to all MSRs by default. 4256 4257``KVM_MSR_FILTER_DEFAULT_DENY`` 4258 4259 If no filter range matches an MSR index that is getting accessed, KVM will 4260 deny accesses to all MSRs by default. 4261 4262This ioctl allows userspace to define up to 16 bitmaps of MSR ranges to deny 4263guest MSR accesses that would normally be allowed by KVM. If an MSR is not 4264covered by a specific range, the "default" filtering behavior applies. Each 4265bitmap range covers MSRs from [base .. base+nmsrs). 4266 4267If an MSR access is denied by userspace, the resulting KVM behavior depends on 4268whether or not KVM_CAP_X86_USER_SPACE_MSR's KVM_MSR_EXIT_REASON_FILTER is 4269enabled. If KVM_MSR_EXIT_REASON_FILTER is enabled, KVM will exit to userspace 4270on denied accesses, i.e. userspace effectively intercepts the MSR access. If 4271KVM_MSR_EXIT_REASON_FILTER is not enabled, KVM will inject a #GP into the guest 4272on denied accesses. Note, if an MSR access is denied during emulation of MSR 4273load/stores during VMX transitions, KVM ignores KVM_MSR_EXIT_REASON_FILTER. 4274See the below warning for full details. 4275 4276If an MSR access is allowed by userspace, KVM will emulate and/or virtualize 4277the access in accordance with the vCPU model. Note, KVM may still ultimately 4278inject a #GP if an access is allowed by userspace, e.g. if KVM doesn't support 4279the MSR, or to follow architectural behavior for the MSR. 4280 4281By default, KVM operates in KVM_MSR_FILTER_DEFAULT_ALLOW mode with no MSR range 4282filters. 4283 4284Calling this ioctl with an empty set of ranges (all nmsrs == 0) disables MSR 4285filtering. In that mode, ``KVM_MSR_FILTER_DEFAULT_DENY`` is invalid and causes 4286an error. 4287 4288.. warning:: 4289 MSR accesses that are side effects of instruction execution (emulated or 4290 native) are not filtered as hardware does not honor MSR bitmaps outside of 4291 RDMSR and WRMSR, and KVM mimics that behavior when emulating instructions 4292 to avoid pointless divergence from hardware. E.g. RDPID reads MSR_TSC_AUX, 4293 SYSENTER reads the SYSENTER MSRs, etc. 4294 4295 MSRs that are loaded/stored via dedicated VMCS fields are not filtered as 4296 part of VM-Enter/VM-Exit emulation. 4297 4298 MSRs that are loaded/store via VMX's load/store lists _are_ filtered as part 4299 of VM-Enter/VM-Exit emulation. If an MSR access is denied on VM-Enter, KVM 4300 synthesizes a consistency check VM-Exit(EXIT_REASON_MSR_LOAD_FAIL). If an 4301 MSR access is denied on VM-Exit, KVM synthesizes a VM-Abort. In short, KVM 4302 extends Intel's architectural list of MSRs that cannot be loaded/saved via 4303 the VM-Enter/VM-Exit MSR list. It is platform owner's responsibility to 4304 to communicate any such restrictions to their end users. 4305 4306 x2APIC MSR accesses cannot be filtered (KVM silently ignores filters that 4307 cover any x2APIC MSRs). 4308 4309Note, invoking this ioctl while a vCPU is running is inherently racy. However, 4310KVM does guarantee that vCPUs will see either the previous filter or the new 4311filter, e.g. MSRs with identical settings in both the old and new filter will 4312have deterministic behavior. 4313 4314Similarly, if userspace wishes to intercept on denied accesses, 4315KVM_MSR_EXIT_REASON_FILTER must be enabled before activating any filters, and 4316left enabled until after all filters are deactivated. Failure to do so may 4317result in KVM injecting a #GP instead of exiting to userspace. 4318 43194.98 KVM_CREATE_SPAPR_TCE_64 4320---------------------------- 4321 4322:Capability: KVM_CAP_SPAPR_TCE_64 4323:Architectures: powerpc 4324:Type: vm ioctl 4325:Parameters: struct kvm_create_spapr_tce_64 (in) 4326:Returns: file descriptor for manipulating the created TCE table 4327 4328This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit 4329windows, described in 4.62 KVM_CREATE_SPAPR_TCE 4330 4331This capability uses extended struct in ioctl interface:: 4332 4333 /* for KVM_CAP_SPAPR_TCE_64 */ 4334 struct kvm_create_spapr_tce_64 { 4335 __u64 liobn; 4336 __u32 page_shift; 4337 __u32 flags; 4338 __u64 offset; /* in pages */ 4339 __u64 size; /* in pages */ 4340 }; 4341 4342The aim of extension is to support an additional bigger DMA window with 4343a variable page size. 4344KVM_CREATE_SPAPR_TCE_64 receives a 64bit window size, an IOMMU page shift and 4345a bus offset of the corresponding DMA window, @size and @offset are numbers 4346of IOMMU pages. 4347 4348@flags are not used at the moment. 4349 4350The rest of functionality is identical to KVM_CREATE_SPAPR_TCE. 4351 43524.99 KVM_REINJECT_CONTROL 4353------------------------- 4354 4355:Capability: KVM_CAP_REINJECT_CONTROL 4356:Architectures: x86 4357:Type: vm ioctl 4358:Parameters: struct kvm_reinject_control (in) 4359:Returns: 0 on success, 4360 -EFAULT if struct kvm_reinject_control cannot be read, 4361 -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier. 4362 4363i8254 (PIT) has two modes, reinject and !reinject. The default is reinject, 4364where KVM queues elapsed i8254 ticks and monitors completion of interrupt from 4365vector(s) that i8254 injects. Reinject mode dequeues a tick and injects its 4366interrupt whenever there isn't a pending interrupt from i8254. 4367!reinject mode injects an interrupt as soon as a tick arrives. 4368 4369:: 4370 4371 struct kvm_reinject_control { 4372 __u8 pit_reinject; 4373 __u8 reserved[31]; 4374 }; 4375 4376pit_reinject = 0 (!reinject mode) is recommended, unless running an old 4377operating system that uses the PIT for timing (e.g. Linux 2.4.x). 4378 43794.100 KVM_PPC_CONFIGURE_V3_MMU 4380------------------------------ 4381 4382:Capability: KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 4383:Architectures: ppc 4384:Type: vm ioctl 4385:Parameters: struct kvm_ppc_mmuv3_cfg (in) 4386:Returns: 0 on success, 4387 -EFAULT if struct kvm_ppc_mmuv3_cfg cannot be read, 4388 -EINVAL if the configuration is invalid 4389 4390This ioctl controls whether the guest will use radix or HPT (hashed 4391page table) translation, and sets the pointer to the process table for 4392the guest. 4393 4394:: 4395 4396 struct kvm_ppc_mmuv3_cfg { 4397 __u64 flags; 4398 __u64 process_table; 4399 }; 4400 4401There are two bits that can be set in flags; KVM_PPC_MMUV3_RADIX and 4402KVM_PPC_MMUV3_GTSE. KVM_PPC_MMUV3_RADIX, if set, configures the guest 4403to use radix tree translation, and if clear, to use HPT translation. 4404KVM_PPC_MMUV3_GTSE, if set and if KVM permits it, configures the guest 4405to be able to use the global TLB and SLB invalidation instructions; 4406if clear, the guest may not use these instructions. 4407 4408The process_table field specifies the address and size of the guest 4409process table, which is in the guest's space. This field is formatted 4410as the second doubleword of the partition table entry, as defined in 4411the Power ISA V3.00, Book III section 5.7.6.1. 4412 44134.101 KVM_PPC_GET_RMMU_INFO 4414--------------------------- 4415 4416:Capability: KVM_CAP_PPC_MMU_RADIX 4417:Architectures: ppc 4418:Type: vm ioctl 4419:Parameters: struct kvm_ppc_rmmu_info (out) 4420:Returns: 0 on success, 4421 -EFAULT if struct kvm_ppc_rmmu_info cannot be written, 4422 -EINVAL if no useful information can be returned 4423 4424This ioctl returns a structure containing two things: (a) a list 4425containing supported radix tree geometries, and (b) a list that maps 4426page sizes to put in the "AP" (actual page size) field for the tlbie 4427(TLB invalidate entry) instruction. 4428 4429:: 4430 4431 struct kvm_ppc_rmmu_info { 4432 struct kvm_ppc_radix_geom { 4433 __u8 page_shift; 4434 __u8 level_bits[4]; 4435 __u8 pad[3]; 4436 } geometries[8]; 4437 __u32 ap_encodings[8]; 4438 }; 4439 4440The geometries[] field gives up to 8 supported geometries for the 4441radix page table, in terms of the log base 2 of the smallest page 4442size, and the number of bits indexed at each level of the tree, from 4443the PTE level up to the PGD level in that order. Any unused entries 4444will have 0 in the page_shift field. 4445 4446The ap_encodings gives the supported page sizes and their AP field 4447encodings, encoded with the AP value in the top 3 bits and the log 4448base 2 of the page size in the bottom 6 bits. 4449 44504.102 KVM_PPC_RESIZE_HPT_PREPARE 4451-------------------------------- 4452 4453:Capability: KVM_CAP_SPAPR_RESIZE_HPT 4454:Architectures: powerpc 4455:Type: vm ioctl 4456:Parameters: struct kvm_ppc_resize_hpt (in) 4457:Returns: 0 on successful completion, 4458 >0 if a new HPT is being prepared, the value is an estimated 4459 number of milliseconds until preparation is complete, 4460 -EFAULT if struct kvm_reinject_control cannot be read, 4461 -EINVAL if the supplied shift or flags are invalid, 4462 -ENOMEM if unable to allocate the new HPT, 4463 4464Used to implement the PAPR extension for runtime resizing of a guest's 4465Hashed Page Table (HPT). Specifically this starts, stops or monitors 4466the preparation of a new potential HPT for the guest, essentially 4467implementing the H_RESIZE_HPT_PREPARE hypercall. 4468 4469:: 4470 4471 struct kvm_ppc_resize_hpt { 4472 __u64 flags; 4473 __u32 shift; 4474 __u32 pad; 4475 }; 4476 4477If called with shift > 0 when there is no pending HPT for the guest, 4478this begins preparation of a new pending HPT of size 2^(shift) bytes. 4479It then returns a positive integer with the estimated number of 4480milliseconds until preparation is complete. 4481 4482If called when there is a pending HPT whose size does not match that 4483requested in the parameters, discards the existing pending HPT and 4484creates a new one as above. 4485 4486If called when there is a pending HPT of the size requested, will: 4487 4488 * If preparation of the pending HPT is already complete, return 0 4489 * If preparation of the pending HPT has failed, return an error 4490 code, then discard the pending HPT. 4491 * If preparation of the pending HPT is still in progress, return an 4492 estimated number of milliseconds until preparation is complete. 4493 4494If called with shift == 0, discards any currently pending HPT and 4495returns 0 (i.e. cancels any in-progress preparation). 4496 4497flags is reserved for future expansion, currently setting any bits in 4498flags will result in an -EINVAL. 4499 4500Normally this will be called repeatedly with the same parameters until 4501it returns <= 0. The first call will initiate preparation, subsequent 4502ones will monitor preparation until it completes or fails. 4503 45044.103 KVM_PPC_RESIZE_HPT_COMMIT 4505------------------------------- 4506 4507:Capability: KVM_CAP_SPAPR_RESIZE_HPT 4508:Architectures: powerpc 4509:Type: vm ioctl 4510:Parameters: struct kvm_ppc_resize_hpt (in) 4511:Returns: 0 on successful completion, 4512 -EFAULT if struct kvm_reinject_control cannot be read, 4513 -EINVAL if the supplied shift or flags are invalid, 4514 -ENXIO is there is no pending HPT, or the pending HPT doesn't 4515 have the requested size, 4516 -EBUSY if the pending HPT is not fully prepared, 4517 -ENOSPC if there was a hash collision when moving existing 4518 HPT entries to the new HPT, 4519 -EIO on other error conditions 4520 4521Used to implement the PAPR extension for runtime resizing of a guest's 4522Hashed Page Table (HPT). Specifically this requests that the guest be 4523transferred to working with the new HPT, essentially implementing the 4524H_RESIZE_HPT_COMMIT hypercall. 4525 4526:: 4527 4528 struct kvm_ppc_resize_hpt { 4529 __u64 flags; 4530 __u32 shift; 4531 __u32 pad; 4532 }; 4533 4534This should only be called after KVM_PPC_RESIZE_HPT_PREPARE has 4535returned 0 with the same parameters. In other cases 4536KVM_PPC_RESIZE_HPT_COMMIT will return an error (usually -ENXIO or 4537-EBUSY, though others may be possible if the preparation was started, 4538but failed). 4539 4540This will have undefined effects on the guest if it has not already 4541placed itself in a quiescent state where no vcpu will make MMU enabled 4542memory accesses. 4543 4544On successful completion, the pending HPT will become the guest's active 4545HPT and the previous HPT will be discarded. 4546 4547On failure, the guest will still be operating on its previous HPT. 4548 45494.104 KVM_X86_GET_MCE_CAP_SUPPORTED 4550----------------------------------- 4551 4552:Capability: KVM_CAP_MCE 4553:Architectures: x86 4554:Type: system ioctl 4555:Parameters: u64 mce_cap (out) 4556:Returns: 0 on success, -1 on error 4557 4558Returns supported MCE capabilities. The u64 mce_cap parameter 4559has the same format as the MSR_IA32_MCG_CAP register. Supported 4560capabilities will have the corresponding bits set. 4561 45624.105 KVM_X86_SETUP_MCE 4563----------------------- 4564 4565:Capability: KVM_CAP_MCE 4566:Architectures: x86 4567:Type: vcpu ioctl 4568:Parameters: u64 mcg_cap (in) 4569:Returns: 0 on success, 4570 -EFAULT if u64 mcg_cap cannot be read, 4571 -EINVAL if the requested number of banks is invalid, 4572 -EINVAL if requested MCE capability is not supported. 4573 4574Initializes MCE support for use. The u64 mcg_cap parameter 4575has the same format as the MSR_IA32_MCG_CAP register and 4576specifies which capabilities should be enabled. The maximum 4577supported number of error-reporting banks can be retrieved when 4578checking for KVM_CAP_MCE. The supported capabilities can be 4579retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED. 4580 45814.106 KVM_X86_SET_MCE 4582--------------------- 4583 4584:Capability: KVM_CAP_MCE 4585:Architectures: x86 4586:Type: vcpu ioctl 4587:Parameters: struct kvm_x86_mce (in) 4588:Returns: 0 on success, 4589 -EFAULT if struct kvm_x86_mce cannot be read, 4590 -EINVAL if the bank number is invalid, 4591 -EINVAL if VAL bit is not set in status field. 4592 4593Inject a machine check error (MCE) into the guest. The input 4594parameter is:: 4595 4596 struct kvm_x86_mce { 4597 __u64 status; 4598 __u64 addr; 4599 __u64 misc; 4600 __u64 mcg_status; 4601 __u8 bank; 4602 __u8 pad1[7]; 4603 __u64 pad2[3]; 4604 }; 4605 4606If the MCE being reported is an uncorrected error, KVM will 4607inject it as an MCE exception into the guest. If the guest 4608MCG_STATUS register reports that an MCE is in progress, KVM 4609causes an KVM_EXIT_SHUTDOWN vmexit. 4610 4611Otherwise, if the MCE is a corrected error, KVM will just 4612store it in the corresponding bank (provided this bank is 4613not holding a previously reported uncorrected error). 4614 46154.107 KVM_S390_GET_CMMA_BITS 4616---------------------------- 4617 4618:Capability: KVM_CAP_S390_CMMA_MIGRATION 4619:Architectures: s390 4620:Type: vm ioctl 4621:Parameters: struct kvm_s390_cmma_log (in, out) 4622:Returns: 0 on success, a negative value on error 4623 4624Errors: 4625 4626 ====== ============================================================= 4627 ENOMEM not enough memory can be allocated to complete the task 4628 ENXIO if CMMA is not enabled 4629 EINVAL if KVM_S390_CMMA_PEEK is not set but migration mode was not enabled 4630 EINVAL if KVM_S390_CMMA_PEEK is not set but dirty tracking has been 4631 disabled (and thus migration mode was automatically disabled) 4632 EFAULT if the userspace address is invalid or if no page table is 4633 present for the addresses (e.g. when using hugepages). 4634 ====== ============================================================= 4635 4636This ioctl is used to get the values of the CMMA bits on the s390 4637architecture. It is meant to be used in two scenarios: 4638 4639- During live migration to save the CMMA values. Live migration needs 4640 to be enabled via the KVM_REQ_START_MIGRATION VM property. 4641- To non-destructively peek at the CMMA values, with the flag 4642 KVM_S390_CMMA_PEEK set. 4643 4644The ioctl takes parameters via the kvm_s390_cmma_log struct. The desired 4645values are written to a buffer whose location is indicated via the "values" 4646member in the kvm_s390_cmma_log struct. The values in the input struct are 4647also updated as needed. 4648 4649Each CMMA value takes up one byte. 4650 4651:: 4652 4653 struct kvm_s390_cmma_log { 4654 __u64 start_gfn; 4655 __u32 count; 4656 __u32 flags; 4657 union { 4658 __u64 remaining; 4659 __u64 mask; 4660 }; 4661 __u64 values; 4662 }; 4663 4664start_gfn is the number of the first guest frame whose CMMA values are 4665to be retrieved, 4666 4667count is the length of the buffer in bytes, 4668 4669values points to the buffer where the result will be written to. 4670 4671If count is greater than KVM_S390_SKEYS_MAX, then it is considered to be 4672KVM_S390_SKEYS_MAX. KVM_S390_SKEYS_MAX is re-used for consistency with 4673other ioctls. 4674 4675The result is written in the buffer pointed to by the field values, and 4676the values of the input parameter are updated as follows. 4677 4678Depending on the flags, different actions are performed. The only 4679supported flag so far is KVM_S390_CMMA_PEEK. 4680 4681The default behaviour if KVM_S390_CMMA_PEEK is not set is: 4682start_gfn will indicate the first page frame whose CMMA bits were dirty. 4683It is not necessarily the same as the one passed as input, as clean pages 4684are skipped. 4685 4686count will indicate the number of bytes actually written in the buffer. 4687It can (and very often will) be smaller than the input value, since the 4688buffer is only filled until 16 bytes of clean values are found (which 4689are then not copied in the buffer). Since a CMMA migration block needs 4690the base address and the length, for a total of 16 bytes, we will send 4691back some clean data if there is some dirty data afterwards, as long as 4692the size of the clean data does not exceed the size of the header. This 4693allows to minimize the amount of data to be saved or transferred over 4694the network at the expense of more roundtrips to userspace. The next 4695invocation of the ioctl will skip over all the clean values, saving 4696potentially more than just the 16 bytes we found. 4697 4698If KVM_S390_CMMA_PEEK is set: 4699the existing storage attributes are read even when not in migration 4700mode, and no other action is performed; 4701 4702the output start_gfn will be equal to the input start_gfn, 4703 4704the output count will be equal to the input count, except if the end of 4705memory has been reached. 4706 4707In both cases: 4708the field "remaining" will indicate the total number of dirty CMMA values 4709still remaining, or 0 if KVM_S390_CMMA_PEEK is set and migration mode is 4710not enabled. 4711 4712mask is unused. 4713 4714values points to the userspace buffer where the result will be stored. 4715 47164.108 KVM_S390_SET_CMMA_BITS 4717---------------------------- 4718 4719:Capability: KVM_CAP_S390_CMMA_MIGRATION 4720:Architectures: s390 4721:Type: vm ioctl 4722:Parameters: struct kvm_s390_cmma_log (in) 4723:Returns: 0 on success, a negative value on error 4724 4725This ioctl is used to set the values of the CMMA bits on the s390 4726architecture. It is meant to be used during live migration to restore 4727the CMMA values, but there are no restrictions on its use. 4728The ioctl takes parameters via the kvm_s390_cmma_values struct. 4729Each CMMA value takes up one byte. 4730 4731:: 4732 4733 struct kvm_s390_cmma_log { 4734 __u64 start_gfn; 4735 __u32 count; 4736 __u32 flags; 4737 union { 4738 __u64 remaining; 4739 __u64 mask; 4740 }; 4741 __u64 values; 4742 }; 4743 4744start_gfn indicates the starting guest frame number, 4745 4746count indicates how many values are to be considered in the buffer, 4747 4748flags is not used and must be 0. 4749 4750mask indicates which PGSTE bits are to be considered. 4751 4752remaining is not used. 4753 4754values points to the buffer in userspace where to store the values. 4755 4756This ioctl can fail with -ENOMEM if not enough memory can be allocated to 4757complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if 4758the count field is too large (e.g. more than KVM_S390_CMMA_SIZE_MAX) or 4759if the flags field was not 0, with -EFAULT if the userspace address is 4760invalid, if invalid pages are written to (e.g. after the end of memory) 4761or if no page table is present for the addresses (e.g. when using 4762hugepages). 4763 47644.109 KVM_PPC_GET_CPU_CHAR 4765-------------------------- 4766 4767:Capability: KVM_CAP_PPC_GET_CPU_CHAR 4768:Architectures: powerpc 4769:Type: vm ioctl 4770:Parameters: struct kvm_ppc_cpu_char (out) 4771:Returns: 0 on successful completion, 4772 -EFAULT if struct kvm_ppc_cpu_char cannot be written 4773 4774This ioctl gives userspace information about certain characteristics 4775of the CPU relating to speculative execution of instructions and 4776possible information leakage resulting from speculative execution (see 4777CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754). The information is 4778returned in struct kvm_ppc_cpu_char, which looks like this:: 4779 4780 struct kvm_ppc_cpu_char { 4781 __u64 character; /* characteristics of the CPU */ 4782 __u64 behaviour; /* recommended software behaviour */ 4783 __u64 character_mask; /* valid bits in character */ 4784 __u64 behaviour_mask; /* valid bits in behaviour */ 4785 }; 4786 4787For extensibility, the character_mask and behaviour_mask fields 4788indicate which bits of character and behaviour have been filled in by 4789the kernel. If the set of defined bits is extended in future then 4790userspace will be able to tell whether it is running on a kernel that 4791knows about the new bits. 4792 4793The character field describes attributes of the CPU which can help 4794with preventing inadvertent information disclosure - specifically, 4795whether there is an instruction to flash-invalidate the L1 data cache 4796(ori 30,30,0 or mtspr SPRN_TRIG2,rN), whether the L1 data cache is set 4797to a mode where entries can only be used by the thread that created 4798them, whether the bcctr[l] instruction prevents speculation, and 4799whether a speculation barrier instruction (ori 31,31,0) is provided. 4800 4801The behaviour field describes actions that software should take to 4802prevent inadvertent information disclosure, and thus describes which 4803vulnerabilities the hardware is subject to; specifically whether the 4804L1 data cache should be flushed when returning to user mode from the 4805kernel, and whether a speculation barrier should be placed between an 4806array bounds check and the array access. 4807 4808These fields use the same bit definitions as the new 4809H_GET_CPU_CHARACTERISTICS hypercall. 4810 48114.110 KVM_MEMORY_ENCRYPT_OP 4812--------------------------- 4813 4814:Capability: basic 4815:Architectures: x86 4816:Type: vm ioctl, vcpu ioctl 4817:Parameters: an opaque platform specific structure (in/out) 4818:Returns: 0 on success; -1 on error 4819 4820If the platform supports creating encrypted VMs then this ioctl can be used 4821for issuing platform-specific memory encryption commands to manage those 4822encrypted VMs. 4823 4824Currently, this ioctl is used for issuing both Secure Encrypted Virtualization 4825(SEV) commands on AMD Processors and Trusted Domain Extensions (TDX) commands 4826on Intel Processors. The detailed commands are defined in 4827Documentation/virt/kvm/x86/amd-memory-encryption.rst and 4828Documentation/virt/kvm/x86/intel-tdx.rst. 4829 48304.111 KVM_MEMORY_ENCRYPT_REG_REGION 4831----------------------------------- 4832 4833:Capability: basic 4834:Architectures: x86 4835:Type: system 4836:Parameters: struct kvm_enc_region (in) 4837:Returns: 0 on success; -1 on error 4838 4839This ioctl can be used to register a guest memory region which may 4840contain encrypted data (e.g. guest RAM, SMRAM etc). 4841 4842It is used in the SEV-enabled guest. When encryption is enabled, a guest 4843memory region may contain encrypted data. The SEV memory encryption 4844engine uses a tweak such that two identical plaintext pages, each at 4845different locations will have differing ciphertexts. So swapping or 4846moving ciphertext of those pages will not result in plaintext being 4847swapped. So relocating (or migrating) physical backing pages for the SEV 4848guest will require some additional steps. 4849 4850Note: The current SEV key management spec does not provide commands to 4851swap or migrate (move) ciphertext pages. Hence, for now we pin the guest 4852memory region registered with the ioctl. 4853 48544.112 KVM_MEMORY_ENCRYPT_UNREG_REGION 4855------------------------------------- 4856 4857:Capability: basic 4858:Architectures: x86 4859:Type: system 4860:Parameters: struct kvm_enc_region (in) 4861:Returns: 0 on success; -1 on error 4862 4863This ioctl can be used to unregister the guest memory region registered 4864with KVM_MEMORY_ENCRYPT_REG_REGION ioctl above. 4865 48664.113 KVM_HYPERV_EVENTFD 4867------------------------ 4868 4869:Capability: KVM_CAP_HYPERV_EVENTFD 4870:Architectures: x86 4871:Type: vm ioctl 4872:Parameters: struct kvm_hyperv_eventfd (in) 4873 4874This ioctl (un)registers an eventfd to receive notifications from the guest on 4875the specified Hyper-V connection id through the SIGNAL_EVENT hypercall, without 4876causing a user exit. SIGNAL_EVENT hypercall with non-zero event flag number 4877(bits 24-31) still triggers a KVM_EXIT_HYPERV_HCALL user exit. 4878 4879:: 4880 4881 struct kvm_hyperv_eventfd { 4882 __u32 conn_id; 4883 __s32 fd; 4884 __u32 flags; 4885 __u32 padding[3]; 4886 }; 4887 4888The conn_id field should fit within 24 bits:: 4889 4890 #define KVM_HYPERV_CONN_ID_MASK 0x00ffffff 4891 4892The acceptable values for the flags field are:: 4893 4894 #define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) 4895 4896:Returns: 0 on success, 4897 -EINVAL if conn_id or flags is outside the allowed range, 4898 -ENOENT on deassign if the conn_id isn't registered, 4899 -EEXIST on assign if the conn_id is already registered 4900 49014.114 KVM_GET_NESTED_STATE 4902-------------------------- 4903 4904:Capability: KVM_CAP_NESTED_STATE 4905:Architectures: x86 4906:Type: vcpu ioctl 4907:Parameters: struct kvm_nested_state (in/out) 4908:Returns: 0 on success, -1 on error 4909 4910Errors: 4911 4912 ===== ============================================================= 4913 E2BIG the total state size exceeds the value of 'size' specified by 4914 the user; the size required will be written into size. 4915 ===== ============================================================= 4916 4917:: 4918 4919 struct kvm_nested_state { 4920 __u16 flags; 4921 __u16 format; 4922 __u32 size; 4923 4924 union { 4925 struct kvm_vmx_nested_state_hdr vmx; 4926 struct kvm_svm_nested_state_hdr svm; 4927 4928 /* Pad the header to 128 bytes. */ 4929 __u8 pad[120]; 4930 } hdr; 4931 4932 union { 4933 struct kvm_vmx_nested_state_data vmx[0]; 4934 struct kvm_svm_nested_state_data svm[0]; 4935 } data; 4936 }; 4937 4938 #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 4939 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 4940 #define KVM_STATE_NESTED_EVMCS 0x00000004 4941 4942 #define KVM_STATE_NESTED_FORMAT_VMX 0 4943 #define KVM_STATE_NESTED_FORMAT_SVM 1 4944 4945 #define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000 4946 4947 #define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE 0x00000001 4948 #define KVM_STATE_NESTED_VMX_SMM_VMXON 0x00000002 4949 4950 #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 4951 4952 struct kvm_vmx_nested_state_hdr { 4953 __u64 vmxon_pa; 4954 __u64 vmcs12_pa; 4955 4956 struct { 4957 __u16 flags; 4958 } smm; 4959 4960 __u32 flags; 4961 __u64 preemption_timer_deadline; 4962 }; 4963 4964 struct kvm_vmx_nested_state_data { 4965 __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; 4966 __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; 4967 }; 4968 4969This ioctl copies the vcpu's nested virtualization state from the kernel to 4970userspace. 4971 4972The maximum size of the state can be retrieved by passing KVM_CAP_NESTED_STATE 4973to the KVM_CHECK_EXTENSION ioctl(). 4974 49754.115 KVM_SET_NESTED_STATE 4976-------------------------- 4977 4978:Capability: KVM_CAP_NESTED_STATE 4979:Architectures: x86 4980:Type: vcpu ioctl 4981:Parameters: struct kvm_nested_state (in) 4982:Returns: 0 on success, -1 on error 4983 4984This copies the vcpu's kvm_nested_state struct from userspace to the kernel. 4985For the definition of struct kvm_nested_state, see KVM_GET_NESTED_STATE. 4986 49874.116 KVM_(UN)REGISTER_COALESCED_MMIO 4988------------------------------------- 4989 4990:Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio) 4991 KVM_CAP_COALESCED_PIO (for coalesced pio) 4992:Architectures: all 4993:Type: vm ioctl 4994:Parameters: struct kvm_coalesced_mmio_zone 4995:Returns: 0 on success, < 0 on error 4996 4997Coalesced I/O is a performance optimization that defers hardware 4998register write emulation so that userspace exits are avoided. It is 4999typically used to reduce the overhead of emulating frequently accessed 5000hardware registers. 5001 5002When a hardware register is configured for coalesced I/O, write accesses 5003do not exit to userspace and their value is recorded in a ring buffer 5004that is shared between kernel and userspace. 5005 5006Coalesced I/O is used if one or more write accesses to a hardware 5007register can be deferred until a read or a write to another hardware 5008register on the same device. This last access will cause a vmexit and 5009userspace will process accesses from the ring buffer before emulating 5010it. That will avoid exiting to userspace on repeated writes. 5011 5012Coalesced pio is based on coalesced mmio. There is little difference 5013between coalesced mmio and pio except that coalesced pio records accesses 5014to I/O ports. 5015 50164.117 KVM_CLEAR_DIRTY_LOG 5017------------------------- 5018 5019:Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 5020:Architectures: x86, arm64, mips 5021:Type: vm ioctl 5022:Parameters: struct kvm_clear_dirty_log (in) 5023:Returns: 0 on success, -1 on error 5024 5025:: 5026 5027 /* for KVM_CLEAR_DIRTY_LOG */ 5028 struct kvm_clear_dirty_log { 5029 __u32 slot; 5030 __u32 num_pages; 5031 __u64 first_page; 5032 union { 5033 void __user *dirty_bitmap; /* one bit per page */ 5034 __u64 padding; 5035 }; 5036 }; 5037 5038The ioctl clears the dirty status of pages in a memory slot, according to 5039the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap 5040field. Bit 0 of the bitmap corresponds to page "first_page" in the 5041memory slot, and num_pages is the size in bits of the input bitmap. 5042first_page must be a multiple of 64; num_pages must also be a multiple of 504364 unless first_page + num_pages is the size of the memory slot. For each 5044bit that is set in the input bitmap, the corresponding page is marked "clean" 5045in KVM's dirty bitmap, and dirty tracking is re-enabled for that page 5046(for example via write-protection, or by clearing the dirty bit in 5047a page table entry). 5048 5049If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of slot field specifies 5050the address space for which you want to clear the dirty status. See 5051KVM_SET_USER_MEMORY_REGION for details on the usage of slot field. 5052 5053This ioctl is mostly useful when KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 5054is enabled; for more information, see the description of the capability. 5055However, it can always be used as long as KVM_CHECK_EXTENSION confirms 5056that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is present. 5057 50584.118 KVM_GET_SUPPORTED_HV_CPUID 5059-------------------------------- 5060 5061:Capability: KVM_CAP_HYPERV_CPUID (vcpu), KVM_CAP_SYS_HYPERV_CPUID (system) 5062:Architectures: x86 5063:Type: system ioctl, vcpu ioctl 5064:Parameters: struct kvm_cpuid2 (in/out) 5065:Returns: 0 on success, -1 on error 5066 5067:: 5068 5069 struct kvm_cpuid2 { 5070 __u32 nent; 5071 __u32 padding; 5072 struct kvm_cpuid_entry2 entries[0]; 5073 }; 5074 5075 struct kvm_cpuid_entry2 { 5076 __u32 function; 5077 __u32 index; 5078 __u32 flags; 5079 __u32 eax; 5080 __u32 ebx; 5081 __u32 ecx; 5082 __u32 edx; 5083 __u32 padding[3]; 5084 }; 5085 5086This ioctl returns x86 cpuid features leaves related to Hyper-V emulation in 5087KVM. Userspace can use the information returned by this ioctl to construct 5088cpuid information presented to guests consuming Hyper-V enlightenments (e.g. 5089Windows or Hyper-V guests). 5090 5091CPUID feature leaves returned by this ioctl are defined by Hyper-V Top Level 5092Functional Specification (TLFS). These leaves can't be obtained with 5093KVM_GET_SUPPORTED_CPUID ioctl because some of them intersect with KVM feature 5094leaves (0x40000000, 0x40000001). 5095 5096Currently, the following list of CPUID leaves are returned: 5097 5098 - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS 5099 - HYPERV_CPUID_INTERFACE 5100 - HYPERV_CPUID_VERSION 5101 - HYPERV_CPUID_FEATURES 5102 - HYPERV_CPUID_ENLIGHTMENT_INFO 5103 - HYPERV_CPUID_IMPLEMENT_LIMITS 5104 - HYPERV_CPUID_NESTED_FEATURES 5105 - HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS 5106 - HYPERV_CPUID_SYNDBG_INTERFACE 5107 - HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES 5108 5109Userspace invokes KVM_GET_SUPPORTED_HV_CPUID by passing a kvm_cpuid2 structure 5110with the 'nent' field indicating the number of entries in the variable-size 5111array 'entries'. If the number of entries is too low to describe all Hyper-V 5112feature leaves, an error (E2BIG) is returned. If the number is more or equal 5113to the number of Hyper-V feature leaves, the 'nent' field is adjusted to the 5114number of valid entries in the 'entries' array, which is then filled. 5115 5116'index' and 'flags' fields in 'struct kvm_cpuid_entry2' are currently reserved, 5117userspace should not expect to get any particular value there. 5118 5119Note, vcpu version of KVM_GET_SUPPORTED_HV_CPUID is currently deprecated. Unlike 5120system ioctl which exposes all supported feature bits unconditionally, vcpu 5121version has the following quirks: 5122 5123- HYPERV_CPUID_NESTED_FEATURES leaf and HV_X64_ENLIGHTENED_VMCS_RECOMMENDED 5124 feature bit are only exposed when Enlightened VMCS was previously enabled 5125 on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS). 5126- HV_STIMER_DIRECT_MODE_AVAILABLE bit is only exposed with in-kernel LAPIC. 5127 (presumes KVM_CREATE_IRQCHIP has already been called). 5128 51294.119 KVM_ARM_VCPU_FINALIZE 5130--------------------------- 5131 5132:Architectures: arm64 5133:Type: vcpu ioctl 5134:Parameters: int feature (in) 5135:Returns: 0 on success, -1 on error 5136 5137Errors: 5138 5139 ====== ============================================================== 5140 EPERM feature not enabled, needs configuration, or already finalized 5141 EINVAL feature unknown or not present 5142 ====== ============================================================== 5143 5144Recognised values for feature: 5145 5146 ===== =========================================== 5147 arm64 KVM_ARM_VCPU_SVE (requires KVM_CAP_ARM_SVE) 5148 ===== =========================================== 5149 5150Finalizes the configuration of the specified vcpu feature. 5151 5152The vcpu must already have been initialised, enabling the affected feature, by 5153means of a successful :ref:`KVM_ARM_VCPU_INIT <KVM_ARM_VCPU_INIT>` call with the 5154appropriate flag set in features[]. 5155 5156For affected vcpu features, this is a mandatory step that must be performed 5157before the vcpu is fully usable. 5158 5159Between KVM_ARM_VCPU_INIT and KVM_ARM_VCPU_FINALIZE, the feature may be 5160configured by use of ioctls such as KVM_SET_ONE_REG. The exact configuration 5161that should be performed and how to do it are feature-dependent. 5162 5163Other calls that depend on a particular feature being finalized, such as 5164KVM_RUN, KVM_GET_REG_LIST, KVM_GET_ONE_REG and KVM_SET_ONE_REG, will fail with 5165-EPERM unless the feature has already been finalized by means of a 5166KVM_ARM_VCPU_FINALIZE call. 5167 5168See KVM_ARM_VCPU_INIT for details of vcpu features that require finalization 5169using this ioctl. 5170 51714.120 KVM_SET_PMU_EVENT_FILTER 5172------------------------------ 5173 5174:Capability: KVM_CAP_PMU_EVENT_FILTER 5175:Architectures: x86 5176:Type: vm ioctl 5177:Parameters: struct kvm_pmu_event_filter (in) 5178:Returns: 0 on success, -1 on error 5179 5180Errors: 5181 5182 ====== ============================================================ 5183 EFAULT args[0] cannot be accessed 5184 EINVAL args[0] contains invalid data in the filter or filter events 5185 E2BIG nevents is too large 5186 EBUSY not enough memory to allocate the filter 5187 ====== ============================================================ 5188 5189:: 5190 5191 struct kvm_pmu_event_filter { 5192 __u32 action; 5193 __u32 nevents; 5194 __u32 fixed_counter_bitmap; 5195 __u32 flags; 5196 __u32 pad[4]; 5197 __u64 events[0]; 5198 }; 5199 5200This ioctl restricts the set of PMU events the guest can program by limiting 5201which event select and unit mask combinations are permitted. 5202 5203The argument holds a list of filter events which will be allowed or denied. 5204 5205Filter events only control general purpose counters; fixed purpose counters 5206are controlled by the fixed_counter_bitmap. 5207 5208Valid values for 'flags':: 5209 5210``0`` 5211 5212To use this mode, clear the 'flags' field. 5213 5214In this mode each event will contain an event select + unit mask. 5215 5216When the guest attempts to program the PMU the guest's event select + 5217unit mask is compared against the filter events to determine whether the 5218guest should have access. 5219 5220``KVM_PMU_EVENT_FLAG_MASKED_EVENTS`` 5221:Capability: KVM_CAP_PMU_EVENT_MASKED_EVENTS 5222 5223In this mode each filter event will contain an event select, mask, match, and 5224exclude value. To encode a masked event use:: 5225 5226 KVM_PMU_ENCODE_MASKED_ENTRY() 5227 5228An encoded event will follow this layout:: 5229 5230 Bits Description 5231 ---- ----------- 5232 7:0 event select (low bits) 5233 15:8 umask match 5234 31:16 unused 5235 35:32 event select (high bits) 5236 36:54 unused 5237 55 exclude bit 5238 63:56 umask mask 5239 5240When the guest attempts to program the PMU, these steps are followed in 5241determining if the guest should have access: 5242 5243 1. Match the event select from the guest against the filter events. 5244 2. If a match is found, match the guest's unit mask to the mask and match 5245 values of the included filter events. 5246 I.e. (unit mask & mask) == match && !exclude. 5247 3. If a match is found, match the guest's unit mask to the mask and match 5248 values of the excluded filter events. 5249 I.e. (unit mask & mask) == match && exclude. 5250 4. 5251 a. If an included match is found and an excluded match is not found, filter 5252 the event. 5253 b. For everything else, do not filter the event. 5254 5. 5255 a. If the event is filtered and it's an allow list, allow the guest to 5256 program the event. 5257 b. If the event is filtered and it's a deny list, do not allow the guest to 5258 program the event. 5259 5260When setting a new pmu event filter, -EINVAL will be returned if any of the 5261unused fields are set or if any of the high bits (35:32) in the event 5262select are set when called on Intel. 5263 5264Valid values for 'action':: 5265 5266 #define KVM_PMU_EVENT_ALLOW 0 5267 #define KVM_PMU_EVENT_DENY 1 5268 5269Via this API, KVM userspace can also control the behavior of the VM's fixed 5270counters (if any) by configuring the "action" and "fixed_counter_bitmap" fields. 5271 5272Specifically, KVM follows the following pseudo-code when determining whether to 5273allow the guest FixCtr[i] to count its pre-defined fixed event:: 5274 5275 FixCtr[i]_is_allowed = (action == ALLOW) && (bitmap & BIT(i)) || 5276 (action == DENY) && !(bitmap & BIT(i)); 5277 FixCtr[i]_is_denied = !FixCtr[i]_is_allowed; 5278 5279KVM always consumes fixed_counter_bitmap, it's userspace's responsibility to 5280ensure fixed_counter_bitmap is set correctly, e.g. if userspace wants to define 5281a filter that only affects general purpose counters. 5282 5283Note, the "events" field also applies to fixed counters' hardcoded event_select 5284and unit_mask values. "fixed_counter_bitmap" has higher priority than "events" 5285if there is a contradiction between the two. 5286 52874.121 KVM_PPC_SVM_OFF 5288--------------------- 5289 5290:Capability: basic 5291:Architectures: powerpc 5292:Type: vm ioctl 5293:Parameters: none 5294:Returns: 0 on successful completion, 5295 5296Errors: 5297 5298 ====== ================================================================ 5299 EINVAL if ultravisor failed to terminate the secure guest 5300 ENOMEM if hypervisor failed to allocate new radix page tables for guest 5301 ====== ================================================================ 5302 5303This ioctl is used to turn off the secure mode of the guest or transition 5304the guest from secure mode to normal mode. This is invoked when the guest 5305is reset. This has no effect if called for a normal guest. 5306 5307This ioctl issues an ultravisor call to terminate the secure guest, 5308unpins the VPA pages and releases all the device pages that are used to 5309track the secure pages by hypervisor. 5310 53114.122 KVM_S390_NORMAL_RESET 5312--------------------------- 5313 5314:Capability: KVM_CAP_S390_VCPU_RESETS 5315:Architectures: s390 5316:Type: vcpu ioctl 5317:Parameters: none 5318:Returns: 0 5319 5320This ioctl resets VCPU registers and control structures according to 5321the cpu reset definition in the POP (Principles Of Operation). 5322 53234.123 KVM_S390_INITIAL_RESET 5324---------------------------- 5325 5326:Capability: basic 5327:Architectures: s390 5328:Type: vcpu ioctl 5329:Parameters: none 5330:Returns: 0 5331 5332This ioctl resets VCPU registers and control structures according to 5333the initial cpu reset definition in the POP. However, the cpu is not 5334put into ESA mode. This reset is a superset of the normal reset. 5335 53364.124 KVM_S390_CLEAR_RESET 5337-------------------------- 5338 5339:Capability: KVM_CAP_S390_VCPU_RESETS 5340:Architectures: s390 5341:Type: vcpu ioctl 5342:Parameters: none 5343:Returns: 0 5344 5345This ioctl resets VCPU registers and control structures according to 5346the clear cpu reset definition in the POP. However, the cpu is not put 5347into ESA mode. This reset is a superset of the initial reset. 5348 5349 53504.125 KVM_S390_PV_COMMAND 5351------------------------- 5352 5353:Capability: KVM_CAP_S390_PROTECTED 5354:Architectures: s390 5355:Type: vm ioctl 5356:Parameters: struct kvm_pv_cmd 5357:Returns: 0 on success, < 0 on error 5358 5359:: 5360 5361 struct kvm_pv_cmd { 5362 __u32 cmd; /* Command to be executed */ 5363 __u16 rc; /* Ultravisor return code */ 5364 __u16 rrc; /* Ultravisor return reason code */ 5365 __u64 data; /* Data or address */ 5366 __u32 flags; /* flags for future extensions. Must be 0 for now */ 5367 __u32 reserved[3]; 5368 }; 5369 5370**Ultravisor return codes** 5371The Ultravisor return (reason) codes are provided by the kernel if a 5372Ultravisor call has been executed to achieve the results expected by 5373the command. Therefore they are independent of the IOCTL return 5374code. If KVM changes `rc`, its value will always be greater than 0 5375hence setting it to 0 before issuing a PV command is advised to be 5376able to detect a change of `rc`. 5377 5378**cmd values:** 5379 5380KVM_PV_ENABLE 5381 Allocate memory and register the VM with the Ultravisor, thereby 5382 donating memory to the Ultravisor that will become inaccessible to 5383 KVM. All existing CPUs are converted to protected ones. After this 5384 command has succeeded, any CPU added via hotplug will become 5385 protected during its creation as well. 5386 5387 Errors: 5388 5389 ===== ============================= 5390 EINTR an unmasked signal is pending 5391 ===== ============================= 5392 5393KVM_PV_DISABLE 5394 Deregister the VM from the Ultravisor and reclaim the memory that had 5395 been donated to the Ultravisor, making it usable by the kernel again. 5396 All registered VCPUs are converted back to non-protected ones. If a 5397 previous protected VM had been prepared for asynchronous teardown with 5398 KVM_PV_ASYNC_CLEANUP_PREPARE and not subsequently torn down with 5399 KVM_PV_ASYNC_CLEANUP_PERFORM, it will be torn down in this call 5400 together with the current protected VM. 5401 5402KVM_PV_VM_SET_SEC_PARMS 5403 Pass the image header from VM memory to the Ultravisor in 5404 preparation of image unpacking and verification. 5405 5406KVM_PV_VM_UNPACK 5407 Unpack (protect and decrypt) a page of the encrypted boot image. 5408 5409KVM_PV_VM_VERIFY 5410 Verify the integrity of the unpacked image. Only if this succeeds, 5411 KVM is allowed to start protected VCPUs. 5412 5413KVM_PV_INFO 5414 :Capability: KVM_CAP_S390_PROTECTED_DUMP 5415 5416 Presents an API that provides Ultravisor related data to userspace 5417 via subcommands. len_max is the size of the user space buffer, 5418 len_written is KVM's indication of how much bytes of that buffer 5419 were actually written to. len_written can be used to determine the 5420 valid fields if more response fields are added in the future. 5421 5422 :: 5423 5424 enum pv_cmd_info_id { 5425 KVM_PV_INFO_VM, 5426 KVM_PV_INFO_DUMP, 5427 }; 5428 5429 struct kvm_s390_pv_info_header { 5430 __u32 id; 5431 __u32 len_max; 5432 __u32 len_written; 5433 __u32 reserved; 5434 }; 5435 5436 struct kvm_s390_pv_info { 5437 struct kvm_s390_pv_info_header header; 5438 struct kvm_s390_pv_info_dump dump; 5439 struct kvm_s390_pv_info_vm vm; 5440 }; 5441 5442**subcommands:** 5443 5444 KVM_PV_INFO_VM 5445 This subcommand provides basic Ultravisor information for PV 5446 hosts. These values are likely also exported as files in the sysfs 5447 firmware UV query interface but they are more easily available to 5448 programs in this API. 5449 5450 The installed calls and feature_indication members provide the 5451 installed UV calls and the UV's other feature indications. 5452 5453 The max_* members provide information about the maximum number of PV 5454 vcpus, PV guests and PV guest memory size. 5455 5456 :: 5457 5458 struct kvm_s390_pv_info_vm { 5459 __u64 inst_calls_list[4]; 5460 __u64 max_cpus; 5461 __u64 max_guests; 5462 __u64 max_guest_addr; 5463 __u64 feature_indication; 5464 }; 5465 5466 5467 KVM_PV_INFO_DUMP 5468 This subcommand provides information related to dumping PV guests. 5469 5470 :: 5471 5472 struct kvm_s390_pv_info_dump { 5473 __u64 dump_cpu_buffer_len; 5474 __u64 dump_config_mem_buffer_per_1m; 5475 __u64 dump_config_finalize_len; 5476 }; 5477 5478KVM_PV_DUMP 5479 :Capability: KVM_CAP_S390_PROTECTED_DUMP 5480 5481 Presents an API that provides calls which facilitate dumping a 5482 protected VM. 5483 5484 :: 5485 5486 struct kvm_s390_pv_dmp { 5487 __u64 subcmd; 5488 __u64 buff_addr; 5489 __u64 buff_len; 5490 __u64 gaddr; /* For dump storage state */ 5491 }; 5492 5493 **subcommands:** 5494 5495 KVM_PV_DUMP_INIT 5496 Initializes the dump process of a protected VM. If this call does 5497 not succeed all other subcommands will fail with -EINVAL. This 5498 subcommand will return -EINVAL if a dump process has not yet been 5499 completed. 5500 5501 Not all PV vms can be dumped, the owner needs to set `dump 5502 allowed` PCF bit 34 in the SE header to allow dumping. 5503 5504 KVM_PV_DUMP_CONFIG_STOR_STATE 5505 Stores `buff_len` bytes of tweak component values starting with 5506 the 1MB block specified by the absolute guest address 5507 (`gaddr`). `buff_len` needs to be `conf_dump_storage_state_len` 5508 aligned and at least >= the `conf_dump_storage_state_len` value 5509 provided by the dump uv_info data. buff_user might be written to 5510 even if an error rc is returned. For instance if we encounter a 5511 fault after writing the first page of data. 5512 5513 KVM_PV_DUMP_COMPLETE 5514 If the subcommand succeeds it completes the dump process and lets 5515 KVM_PV_DUMP_INIT be called again. 5516 5517 On success `conf_dump_finalize_len` bytes of completion data will be 5518 stored to the `buff_addr`. The completion data contains a key 5519 derivation seed, IV, tweak nonce and encryption keys as well as an 5520 authentication tag all of which are needed to decrypt the dump at a 5521 later time. 5522 5523KVM_PV_ASYNC_CLEANUP_PREPARE 5524 :Capability: KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 5525 5526 Prepare the current protected VM for asynchronous teardown. Most 5527 resources used by the current protected VM will be set aside for a 5528 subsequent asynchronous teardown. The current protected VM will then 5529 resume execution immediately as non-protected. There can be at most 5530 one protected VM prepared for asynchronous teardown at any time. If 5531 a protected VM had already been prepared for teardown without 5532 subsequently calling KVM_PV_ASYNC_CLEANUP_PERFORM, this call will 5533 fail. In that case, the userspace process should issue a normal 5534 KVM_PV_DISABLE. The resources set aside with this call will need to 5535 be cleaned up with a subsequent call to KVM_PV_ASYNC_CLEANUP_PERFORM 5536 or KVM_PV_DISABLE, otherwise they will be cleaned up when KVM 5537 terminates. KVM_PV_ASYNC_CLEANUP_PREPARE can be called again as soon 5538 as cleanup starts, i.e. before KVM_PV_ASYNC_CLEANUP_PERFORM finishes. 5539 5540KVM_PV_ASYNC_CLEANUP_PERFORM 5541 :Capability: KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 5542 5543 Tear down the protected VM previously prepared for teardown with 5544 KVM_PV_ASYNC_CLEANUP_PREPARE. The resources that had been set aside 5545 will be freed during the execution of this command. This PV command 5546 should ideally be issued by userspace from a separate thread. If a 5547 fatal signal is received (or the process terminates naturally), the 5548 command will terminate immediately without completing, and the normal 5549 KVM shutdown procedure will take care of cleaning up all remaining 5550 protected VMs, including the ones whose teardown was interrupted by 5551 process termination. 5552 55534.126 KVM_XEN_HVM_SET_ATTR 5554-------------------------- 5555 5556:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO 5557:Architectures: x86 5558:Type: vm ioctl 5559:Parameters: struct kvm_xen_hvm_attr 5560:Returns: 0 on success, < 0 on error 5561 5562:: 5563 5564 struct kvm_xen_hvm_attr { 5565 __u16 type; 5566 __u16 pad[3]; 5567 union { 5568 __u8 long_mode; 5569 __u8 vector; 5570 __u8 runstate_update_flag; 5571 union { 5572 __u64 gfn; 5573 __u64 hva; 5574 } shared_info; 5575 struct { 5576 __u32 send_port; 5577 __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ 5578 __u32 flags; 5579 union { 5580 struct { 5581 __u32 port; 5582 __u32 vcpu; 5583 __u32 priority; 5584 } port; 5585 struct { 5586 __u32 port; /* Zero for eventfd */ 5587 __s32 fd; 5588 } eventfd; 5589 __u32 padding[4]; 5590 } deliver; 5591 } evtchn; 5592 __u32 xen_version; 5593 __u64 pad[8]; 5594 } u; 5595 }; 5596 5597type values: 5598 5599KVM_XEN_ATTR_TYPE_LONG_MODE 5600 Sets the ABI mode of the VM to 32-bit or 64-bit (long mode). This 5601 determines the layout of the shared_info page exposed to the VM. 5602 5603KVM_XEN_ATTR_TYPE_SHARED_INFO 5604 Sets the guest physical frame number at which the Xen shared_info 5605 page resides. Note that although Xen places vcpu_info for the first 5606 32 vCPUs in the shared_info page, KVM does not automatically do so 5607 and instead requires that KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO or 5608 KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA be used explicitly even when 5609 the vcpu_info for a given vCPU resides at the "default" location 5610 in the shared_info page. This is because KVM may not be aware of 5611 the Xen CPU id which is used as the index into the vcpu_info[] 5612 array, so may know the correct default location. 5613 5614 Note that the shared_info page may be constantly written to by KVM; 5615 it contains the event channel bitmap used to deliver interrupts to 5616 a Xen guest, amongst other things. It is exempt from dirty tracking 5617 mechanisms — KVM will not explicitly mark the page as dirty each 5618 time an event channel interrupt is delivered to the guest! Thus, 5619 userspace should always assume that the designated GFN is dirty if 5620 any vCPU has been running or any event channel interrupts can be 5621 routed to the guest. 5622 5623 Setting the gfn to KVM_XEN_INVALID_GFN will disable the shared_info 5624 page. 5625 5626KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA 5627 If the KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA flag is also set in the 5628 Xen capabilities, then this attribute may be used to set the 5629 userspace address at which the shared_info page resides, which 5630 will always be fixed in the VMM regardless of where it is mapped 5631 in guest physical address space. This attribute should be used in 5632 preference to KVM_XEN_ATTR_TYPE_SHARED_INFO as it avoids 5633 unnecessary invalidation of an internal cache when the page is 5634 re-mapped in guest physical address space. 5635 5636 Setting the hva to zero will disable the shared_info page. 5637 5638KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 5639 Sets the exception vector used to deliver Xen event channel upcalls. 5640 This is the HVM-wide vector injected directly by the hypervisor 5641 (not through the local APIC), typically configured by a guest via 5642 HVM_PARAM_CALLBACK_IRQ. This can be disabled again (e.g. for guest 5643 SHUTDOWN_soft_reset) by setting it to zero. 5644 5645KVM_XEN_ATTR_TYPE_EVTCHN 5646 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates 5647 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures 5648 an outbound port number for interception of EVTCHNOP_send requests 5649 from the guest. A given sending port number may be directed back to 5650 a specified vCPU (by APIC ID) / port / priority on the guest, or to 5651 trigger events on an eventfd. The vCPU and priority can be changed 5652 by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, but other 5653 fields cannot change for a given sending port. A port mapping is 5654 removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags field. Passing 5655 KVM_XEN_EVTCHN_RESET in the flags field removes all interception of 5656 outbound event channels. The values of the flags field are mutually 5657 exclusive and cannot be combined as a bitmask. 5658 5659KVM_XEN_ATTR_TYPE_XEN_VERSION 5660 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates 5661 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures 5662 the 32-bit version code returned to the guest when it invokes the 5663 XENVER_version call; typically (XEN_MAJOR << 16 | XEN_MINOR). PV 5664 Xen guests will often use this to as a dummy hypercall to trigger 5665 event channel delivery, so responding within the kernel without 5666 exiting to userspace is beneficial. 5667 5668KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 5669 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates 5670 support for KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG. It enables the 5671 XEN_RUNSTATE_UPDATE flag which allows guest vCPUs to safely read 5672 other vCPUs' vcpu_runstate_info. Xen guests enable this feature via 5673 the VMASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist 5674 hypercall. 5675 56764.127 KVM_XEN_HVM_GET_ATTR 5677-------------------------- 5678 5679:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO 5680:Architectures: x86 5681:Type: vm ioctl 5682:Parameters: struct kvm_xen_hvm_attr 5683:Returns: 0 on success, < 0 on error 5684 5685Allows Xen VM attributes to be read. For the structure and types, 5686see KVM_XEN_HVM_SET_ATTR above. The KVM_XEN_ATTR_TYPE_EVTCHN 5687attribute cannot be read. 5688 56894.128 KVM_XEN_VCPU_SET_ATTR 5690--------------------------- 5691 5692:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO 5693:Architectures: x86 5694:Type: vcpu ioctl 5695:Parameters: struct kvm_xen_vcpu_attr 5696:Returns: 0 on success, < 0 on error 5697 5698:: 5699 5700 struct kvm_xen_vcpu_attr { 5701 __u16 type; 5702 __u16 pad[3]; 5703 union { 5704 __u64 gpa; 5705 __u64 pad[4]; 5706 struct { 5707 __u64 state; 5708 __u64 state_entry_time; 5709 __u64 time_running; 5710 __u64 time_runnable; 5711 __u64 time_blocked; 5712 __u64 time_offline; 5713 } runstate; 5714 __u32 vcpu_id; 5715 struct { 5716 __u32 port; 5717 __u32 priority; 5718 __u64 expires_ns; 5719 } timer; 5720 __u8 vector; 5721 } u; 5722 }; 5723 5724type values: 5725 5726KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 5727 Sets the guest physical address of the vcpu_info for a given vCPU. 5728 As with the shared_info page for the VM, the corresponding page may be 5729 dirtied at any time if event channel interrupt delivery is enabled, so 5730 userspace should always assume that the page is dirty without relying 5731 on dirty logging. Setting the gpa to KVM_XEN_INVALID_GPA will disable 5732 the vcpu_info. 5733 5734KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA 5735 If the KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA flag is also set in the 5736 Xen capabilities, then this attribute may be used to set the 5737 userspace address of the vcpu_info for a given vCPU. It should 5738 only be used when the vcpu_info resides at the "default" location 5739 in the shared_info page. In this case it is safe to assume the 5740 userspace address will not change, because the shared_info page is 5741 an overlay on guest memory and remains at a fixed host address 5742 regardless of where it is mapped in guest physical address space 5743 and hence unnecessary invalidation of an internal cache may be 5744 avoided if the guest memory layout is modified. 5745 If the vcpu_info does not reside at the "default" location then 5746 it is not guaranteed to remain at the same host address and 5747 hence the aforementioned cache invalidation is required. 5748 5749KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 5750 Sets the guest physical address of an additional pvclock structure 5751 for a given vCPU. This is typically used for guest vsyscall support. 5752 Setting the gpa to KVM_XEN_INVALID_GPA will disable the structure. 5753 5754KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 5755 Sets the guest physical address of the vcpu_runstate_info for a given 5756 vCPU. This is how a Xen guest tracks CPU state such as steal time. 5757 Setting the gpa to KVM_XEN_INVALID_GPA will disable the runstate area. 5758 5759KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 5760 Sets the runstate (RUNSTATE_running/_runnable/_blocked/_offline) of 5761 the given vCPU from the .u.runstate.state member of the structure. 5762 KVM automatically accounts running and runnable time but blocked 5763 and offline states are only entered explicitly. 5764 5765KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 5766 Sets all fields of the vCPU runstate data from the .u.runstate member 5767 of the structure, including the current runstate. The state_entry_time 5768 must equal the sum of the other four times. 5769 5770KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 5771 This *adds* the contents of the .u.runstate members of the structure 5772 to the corresponding members of the given vCPU's runstate data, thus 5773 permitting atomic adjustments to the runstate times. The adjustment 5774 to the state_entry_time must equal the sum of the adjustments to the 5775 other four times. The state field must be set to -1, or to a valid 5776 runstate value (RUNSTATE_running, RUNSTATE_runnable, RUNSTATE_blocked 5777 or RUNSTATE_offline) to set the current accounted state as of the 5778 adjusted state_entry_time. 5779 5780KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 5781 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates 5782 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the Xen 5783 vCPU ID of the given vCPU, to allow timer-related VCPU operations to 5784 be intercepted by KVM. 5785 5786KVM_XEN_VCPU_ATTR_TYPE_TIMER 5787 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates 5788 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the 5789 event channel port/priority for the VIRQ_TIMER of the vCPU, as well 5790 as allowing a pending timer to be saved/restored. Setting the timer 5791 port to zero disables kernel handling of the singleshot timer. 5792 5793KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 5794 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates 5795 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the 5796 per-vCPU local APIC upcall vector, configured by a Xen guest with 5797 the HVMOP_set_evtchn_upcall_vector hypercall. This is typically 5798 used by Windows guests, and is distinct from the HVM-wide upcall 5799 vector configured with HVM_PARAM_CALLBACK_IRQ. It is disabled by 5800 setting the vector to zero. 5801 5802 58034.129 KVM_XEN_VCPU_GET_ATTR 5804--------------------------- 5805 5806:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO 5807:Architectures: x86 5808:Type: vcpu ioctl 5809:Parameters: struct kvm_xen_vcpu_attr 5810:Returns: 0 on success, < 0 on error 5811 5812Allows Xen vCPU attributes to be read. For the structure and types, 5813see KVM_XEN_VCPU_SET_ATTR above. 5814 5815The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST type may not be used 5816with the KVM_XEN_VCPU_GET_ATTR ioctl. 5817 58184.130 KVM_ARM_MTE_COPY_TAGS 5819--------------------------- 5820 5821:Capability: KVM_CAP_ARM_MTE 5822:Architectures: arm64 5823:Type: vm ioctl 5824:Parameters: struct kvm_arm_copy_mte_tags 5825:Returns: number of bytes copied, < 0 on error (-EINVAL for incorrect 5826 arguments, -EFAULT if memory cannot be accessed). 5827 5828:: 5829 5830 struct kvm_arm_copy_mte_tags { 5831 __u64 guest_ipa; 5832 __u64 length; 5833 void __user *addr; 5834 __u64 flags; 5835 __u64 reserved[2]; 5836 }; 5837 5838Copies Memory Tagging Extension (MTE) tags to/from guest tag memory. The 5839``guest_ipa`` and ``length`` fields must be ``PAGE_SIZE`` aligned. 5840``length`` must not be bigger than 2^31 - PAGE_SIZE bytes. The ``addr`` 5841field must point to a buffer which the tags will be copied to or from. 5842 5843``flags`` specifies the direction of copy, either ``KVM_ARM_TAGS_TO_GUEST`` or 5844``KVM_ARM_TAGS_FROM_GUEST``. 5845 5846The size of the buffer to store the tags is ``(length / 16)`` bytes 5847(granules in MTE are 16 bytes long). Each byte contains a single tag 5848value. This matches the format of ``PTRACE_PEEKMTETAGS`` and 5849``PTRACE_POKEMTETAGS``. 5850 5851If an error occurs before any data is copied then a negative error code is 5852returned. If some tags have been copied before an error occurs then the number 5853of bytes successfully copied is returned. If the call completes successfully 5854then ``length`` is returned. 5855 58564.131 KVM_GET_SREGS2 5857-------------------- 5858 5859:Capability: KVM_CAP_SREGS2 5860:Architectures: x86 5861:Type: vcpu ioctl 5862:Parameters: struct kvm_sregs2 (out) 5863:Returns: 0 on success, -1 on error 5864 5865Reads special registers from the vcpu. 5866This ioctl (when supported) replaces the KVM_GET_SREGS. 5867 5868:: 5869 5870 struct kvm_sregs2 { 5871 /* out (KVM_GET_SREGS2) / in (KVM_SET_SREGS2) */ 5872 struct kvm_segment cs, ds, es, fs, gs, ss; 5873 struct kvm_segment tr, ldt; 5874 struct kvm_dtable gdt, idt; 5875 __u64 cr0, cr2, cr3, cr4, cr8; 5876 __u64 efer; 5877 __u64 apic_base; 5878 __u64 flags; 5879 __u64 pdptrs[4]; 5880 }; 5881 5882flags values for ``kvm_sregs2``: 5883 5884``KVM_SREGS2_FLAGS_PDPTRS_VALID`` 5885 5886 Indicates that the struct contains valid PDPTR values. 5887 5888 58894.132 KVM_SET_SREGS2 5890-------------------- 5891 5892:Capability: KVM_CAP_SREGS2 5893:Architectures: x86 5894:Type: vcpu ioctl 5895:Parameters: struct kvm_sregs2 (in) 5896:Returns: 0 on success, -1 on error 5897 5898Writes special registers into the vcpu. 5899See KVM_GET_SREGS2 for the data structures. 5900This ioctl (when supported) replaces the KVM_SET_SREGS. 5901 59024.133 KVM_GET_STATS_FD 5903---------------------- 5904 5905:Capability: KVM_CAP_STATS_BINARY_FD 5906:Architectures: all 5907:Type: vm ioctl, vcpu ioctl 5908:Parameters: none 5909:Returns: statistics file descriptor on success, < 0 on error 5910 5911Errors: 5912 5913 ====== ====================================================== 5914 ENOMEM if the fd could not be created due to lack of memory 5915 EMFILE if the number of opened files exceeds the limit 5916 ====== ====================================================== 5917 5918The returned file descriptor can be used to read VM/vCPU statistics data in 5919binary format. The data in the file descriptor consists of four blocks 5920organized as follows: 5921 5922+-------------+ 5923| Header | 5924+-------------+ 5925| id string | 5926+-------------+ 5927| Descriptors | 5928+-------------+ 5929| Stats Data | 5930+-------------+ 5931 5932Apart from the header starting at offset 0, please be aware that it is 5933not guaranteed that the four blocks are adjacent or in the above order; 5934the offsets of the id, descriptors and data blocks are found in the 5935header. However, all four blocks are aligned to 64 bit offsets in the 5936file and they do not overlap. 5937 5938All blocks except the data block are immutable. Userspace can read them 5939only one time after retrieving the file descriptor, and then use ``pread`` or 5940``lseek`` to read the statistics repeatedly. 5941 5942All data is in system endianness. 5943 5944The format of the header is as follows:: 5945 5946 struct kvm_stats_header { 5947 __u32 flags; 5948 __u32 name_size; 5949 __u32 num_desc; 5950 __u32 id_offset; 5951 __u32 desc_offset; 5952 __u32 data_offset; 5953 }; 5954 5955The ``flags`` field is not used at the moment. It is always read as 0. 5956 5957The ``name_size`` field is the size (in byte) of the statistics name string 5958(including trailing '\0') which is contained in the "id string" block and 5959appended at the end of every descriptor. 5960 5961The ``num_desc`` field is the number of descriptors that are included in the 5962descriptor block. (The actual number of values in the data block may be 5963larger, since each descriptor may comprise more than one value). 5964 5965The ``id_offset`` field is the offset of the id string from the start of the 5966file indicated by the file descriptor. It is a multiple of 8. 5967 5968The ``desc_offset`` field is the offset of the Descriptors block from the start 5969of the file indicated by the file descriptor. It is a multiple of 8. 5970 5971The ``data_offset`` field is the offset of the Stats Data block from the start 5972of the file indicated by the file descriptor. It is a multiple of 8. 5973 5974The id string block contains a string which identifies the file descriptor on 5975which KVM_GET_STATS_FD was invoked. The size of the block, including the 5976trailing ``'\0'``, is indicated by the ``name_size`` field in the header. 5977 5978The descriptors block is only needed to be read once for the lifetime of the 5979file descriptor contains a sequence of ``struct kvm_stats_desc``, each followed 5980by a string of size ``name_size``. 5981:: 5982 5983 #define KVM_STATS_TYPE_SHIFT 0 5984 #define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT) 5985 #define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) 5986 #define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) 5987 #define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT) 5988 #define KVM_STATS_TYPE_LINEAR_HIST (0x3 << KVM_STATS_TYPE_SHIFT) 5989 #define KVM_STATS_TYPE_LOG_HIST (0x4 << KVM_STATS_TYPE_SHIFT) 5990 #define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_LOG_HIST 5991 5992 #define KVM_STATS_UNIT_SHIFT 4 5993 #define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) 5994 #define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT) 5995 #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) 5996 #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) 5997 #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) 5998 #define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT) 5999 #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_BOOLEAN 6000 6001 #define KVM_STATS_BASE_SHIFT 8 6002 #define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) 6003 #define KVM_STATS_BASE_POW10 (0x0 << KVM_STATS_BASE_SHIFT) 6004 #define KVM_STATS_BASE_POW2 (0x1 << KVM_STATS_BASE_SHIFT) 6005 #define KVM_STATS_BASE_MAX KVM_STATS_BASE_POW2 6006 6007 struct kvm_stats_desc { 6008 __u32 flags; 6009 __s16 exponent; 6010 __u16 size; 6011 __u32 offset; 6012 __u32 bucket_size; 6013 char name[]; 6014 }; 6015 6016The ``flags`` field contains the type and unit of the statistics data described 6017by this descriptor. Its endianness is CPU native. 6018The following flags are supported: 6019 6020Bits 0-3 of ``flags`` encode the type: 6021 6022 * ``KVM_STATS_TYPE_CUMULATIVE`` 6023 The statistics reports a cumulative count. The value of data can only be increased. 6024 Most of the counters used in KVM are of this type. 6025 The corresponding ``size`` field for this type is always 1. 6026 All cumulative statistics data are read/write. 6027 * ``KVM_STATS_TYPE_INSTANT`` 6028 The statistics reports an instantaneous value. Its value can be increased or 6029 decreased. This type is usually used as a measurement of some resources, 6030 like the number of dirty pages, the number of large pages, etc. 6031 All instant statistics are read only. 6032 The corresponding ``size`` field for this type is always 1. 6033 * ``KVM_STATS_TYPE_PEAK`` 6034 The statistics data reports a peak value, for example the maximum number 6035 of items in a hash table bucket, the longest time waited and so on. 6036 The value of data can only be increased. 6037 The corresponding ``size`` field for this type is always 1. 6038 * ``KVM_STATS_TYPE_LINEAR_HIST`` 6039 The statistic is reported as a linear histogram. The number of 6040 buckets is specified by the ``size`` field. The size of buckets is specified 6041 by the ``hist_param`` field. The range of the Nth bucket (1 <= N < ``size``) 6042 is [``hist_param``*(N-1), ``hist_param``*N), while the range of the last 6043 bucket is [``hist_param``*(``size``-1), +INF). (+INF means positive infinity 6044 value.) 6045 * ``KVM_STATS_TYPE_LOG_HIST`` 6046 The statistic is reported as a logarithmic histogram. The number of 6047 buckets is specified by the ``size`` field. The range of the first bucket is 6048 [0, 1), while the range of the last bucket is [pow(2, ``size``-2), +INF). 6049 Otherwise, The Nth bucket (1 < N < ``size``) covers 6050 [pow(2, N-2), pow(2, N-1)). 6051 6052Bits 4-7 of ``flags`` encode the unit: 6053 6054 * ``KVM_STATS_UNIT_NONE`` 6055 There is no unit for the value of statistics data. This usually means that 6056 the value is a simple counter of an event. 6057 * ``KVM_STATS_UNIT_BYTES`` 6058 It indicates that the statistics data is used to measure memory size, in the 6059 unit of Byte, KiByte, MiByte, GiByte, etc. The unit of the data is 6060 determined by the ``exponent`` field in the descriptor. 6061 * ``KVM_STATS_UNIT_SECONDS`` 6062 It indicates that the statistics data is used to measure time or latency. 6063 * ``KVM_STATS_UNIT_CYCLES`` 6064 It indicates that the statistics data is used to measure CPU clock cycles. 6065 * ``KVM_STATS_UNIT_BOOLEAN`` 6066 It indicates that the statistic will always be either 0 or 1. Boolean 6067 statistics of "peak" type will never go back from 1 to 0. Boolean 6068 statistics can be linear histograms (with two buckets) but not logarithmic 6069 histograms. 6070 6071Note that, in the case of histograms, the unit applies to the bucket 6072ranges, while the bucket value indicates how many samples fell in the 6073bucket's range. 6074 6075Bits 8-11 of ``flags``, together with ``exponent``, encode the scale of the 6076unit: 6077 6078 * ``KVM_STATS_BASE_POW10`` 6079 The scale is based on power of 10. It is used for measurement of time and 6080 CPU clock cycles. For example, an exponent of -9 can be used with 6081 ``KVM_STATS_UNIT_SECONDS`` to express that the unit is nanoseconds. 6082 * ``KVM_STATS_BASE_POW2`` 6083 The scale is based on power of 2. It is used for measurement of memory size. 6084 For example, an exponent of 20 can be used with ``KVM_STATS_UNIT_BYTES`` to 6085 express that the unit is MiB. 6086 6087The ``size`` field is the number of values of this statistics data. Its 6088value is usually 1 for most of simple statistics. 1 means it contains an 6089unsigned 64bit data. 6090 6091The ``offset`` field is the offset from the start of Data Block to the start of 6092the corresponding statistics data. 6093 6094The ``bucket_size`` field is used as a parameter for histogram statistics data. 6095It is only used by linear histogram statistics data, specifying the size of a 6096bucket in the unit expressed by bits 4-11 of ``flags`` together with ``exponent``. 6097 6098The ``name`` field is the name string of the statistics data. The name string 6099starts at the end of ``struct kvm_stats_desc``. The maximum length including 6100the trailing ``'\0'``, is indicated by ``name_size`` in the header. 6101 6102The Stats Data block contains an array of 64-bit values in the same order 6103as the descriptors in Descriptors block. 6104 61054.134 KVM_GET_XSAVE2 6106-------------------- 6107 6108:Capability: KVM_CAP_XSAVE2 6109:Architectures: x86 6110:Type: vcpu ioctl 6111:Parameters: struct kvm_xsave (out) 6112:Returns: 0 on success, -1 on error 6113 6114 6115:: 6116 6117 struct kvm_xsave { 6118 __u32 region[1024]; 6119 __u32 extra[0]; 6120 }; 6121 6122This ioctl would copy current vcpu's xsave struct to the userspace. It 6123copies as many bytes as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) 6124when invoked on the vm file descriptor. The size value returned by 6125KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) will always be at least 4096. 6126Currently, it is only greater than 4096 if a dynamic feature has been 6127enabled with ``arch_prctl()``, but this may change in the future. 6128 6129The offsets of the state save areas in struct kvm_xsave follow the contents 6130of CPUID leaf 0xD on the host. 6131 61324.135 KVM_XEN_HVM_EVTCHN_SEND 6133----------------------------- 6134 6135:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND 6136:Architectures: x86 6137:Type: vm ioctl 6138:Parameters: struct kvm_irq_routing_xen_evtchn 6139:Returns: 0 on success, < 0 on error 6140 6141 6142:: 6143 6144 struct kvm_irq_routing_xen_evtchn { 6145 __u32 port; 6146 __u32 vcpu; 6147 __u32 priority; 6148 }; 6149 6150This ioctl injects an event channel interrupt directly to the guest vCPU. 6151 61524.136 KVM_S390_PV_CPU_COMMAND 6153----------------------------- 6154 6155:Capability: KVM_CAP_S390_PROTECTED_DUMP 6156:Architectures: s390 6157:Type: vcpu ioctl 6158:Parameters: none 6159:Returns: 0 on success, < 0 on error 6160 6161This ioctl closely mirrors `KVM_S390_PV_COMMAND` but handles requests 6162for vcpus. It re-uses the kvm_s390_pv_dmp struct and hence also shares 6163the command ids. 6164 6165**command:** 6166 6167KVM_PV_DUMP 6168 Presents an API that provides calls which facilitate dumping a vcpu 6169 of a protected VM. 6170 6171**subcommand:** 6172 6173KVM_PV_DUMP_CPU 6174 Provides encrypted dump data like register values. 6175 The length of the returned data is provided by uv_info.guest_cpu_stor_len. 6176 61774.137 KVM_S390_ZPCI_OP 6178---------------------- 6179 6180:Capability: KVM_CAP_S390_ZPCI_OP 6181:Architectures: s390 6182:Type: vm ioctl 6183:Parameters: struct kvm_s390_zpci_op (in) 6184:Returns: 0 on success, <0 on error 6185 6186Used to manage hardware-assisted virtualization features for zPCI devices. 6187 6188Parameters are specified via the following structure:: 6189 6190 struct kvm_s390_zpci_op { 6191 /* in */ 6192 __u32 fh; /* target device */ 6193 __u8 op; /* operation to perform */ 6194 __u8 pad[3]; 6195 union { 6196 /* for KVM_S390_ZPCIOP_REG_AEN */ 6197 struct { 6198 __u64 ibv; /* Guest addr of interrupt bit vector */ 6199 __u64 sb; /* Guest addr of summary bit */ 6200 __u32 flags; 6201 __u32 noi; /* Number of interrupts */ 6202 __u8 isc; /* Guest interrupt subclass */ 6203 __u8 sbo; /* Offset of guest summary bit vector */ 6204 __u16 pad; 6205 } reg_aen; 6206 __u64 reserved[8]; 6207 } u; 6208 }; 6209 6210The type of operation is specified in the "op" field. 6211KVM_S390_ZPCIOP_REG_AEN is used to register the VM for adapter event 6212notification interpretation, which will allow firmware delivery of adapter 6213events directly to the vm, with KVM providing a backup delivery mechanism; 6214KVM_S390_ZPCIOP_DEREG_AEN is used to subsequently disable interpretation of 6215adapter event notifications. 6216 6217The target zPCI function must also be specified via the "fh" field. For the 6218KVM_S390_ZPCIOP_REG_AEN operation, additional information to establish firmware 6219delivery must be provided via the "reg_aen" struct. 6220 6221The "pad" and "reserved" fields may be used for future extensions and should be 6222set to 0s by userspace. 6223 62244.138 KVM_ARM_SET_COUNTER_OFFSET 6225-------------------------------- 6226 6227:Capability: KVM_CAP_COUNTER_OFFSET 6228:Architectures: arm64 6229:Type: vm ioctl 6230:Parameters: struct kvm_arm_counter_offset (in) 6231:Returns: 0 on success, < 0 on error 6232 6233This capability indicates that userspace is able to apply a single VM-wide 6234offset to both the virtual and physical counters as viewed by the guest 6235using the KVM_ARM_SET_CNT_OFFSET ioctl and the following data structure: 6236 6237:: 6238 6239 struct kvm_arm_counter_offset { 6240 __u64 counter_offset; 6241 __u64 reserved; 6242 }; 6243 6244The offset describes a number of counter cycles that are subtracted from 6245both virtual and physical counter views (similar to the effects of the 6246CNTVOFF_EL2 and CNTPOFF_EL2 system registers, but only global). The offset 6247always applies to all vcpus (already created or created after this ioctl) 6248for this VM. 6249 6250It is userspace's responsibility to compute the offset based, for example, 6251on previous values of the guest counters. 6252 6253Any value other than 0 for the "reserved" field may result in an error 6254(-EINVAL) being returned. This ioctl can also return -EBUSY if any vcpu 6255ioctl is issued concurrently. 6256 6257Note that using this ioctl results in KVM ignoring subsequent userspace 6258writes to the CNTVCT_EL0 and CNTPCT_EL0 registers using the SET_ONE_REG 6259interface. No error will be returned, but the resulting offset will not be 6260applied. 6261 6262.. _KVM_ARM_GET_REG_WRITABLE_MASKS: 6263 62644.139 KVM_ARM_GET_REG_WRITABLE_MASKS 6265------------------------------------ 6266 6267:Capability: KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 6268:Architectures: arm64 6269:Type: vm ioctl 6270:Parameters: struct reg_mask_range (in/out) 6271:Returns: 0 on success, < 0 on error 6272 6273 6274:: 6275 6276 #define KVM_ARM_FEATURE_ID_RANGE 0 6277 #define KVM_ARM_FEATURE_ID_RANGE_SIZE (3 * 8 * 8) 6278 6279 struct reg_mask_range { 6280 __u64 addr; /* Pointer to mask array */ 6281 __u32 range; /* Requested range */ 6282 __u32 reserved[13]; 6283 }; 6284 6285This ioctl copies the writable masks for a selected range of registers to 6286userspace. 6287 6288The ``addr`` field is a pointer to the destination array where KVM copies 6289the writable masks. 6290 6291The ``range`` field indicates the requested range of registers. 6292``KVM_CHECK_EXTENSION`` for the ``KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES`` 6293capability returns the supported ranges, expressed as a set of flags. Each 6294flag's bit index represents a possible value for the ``range`` field. 6295All other values are reserved for future use and KVM may return an error. 6296 6297The ``reserved[13]`` array is reserved for future use and should be 0, or 6298KVM may return an error. 6299 6300KVM_ARM_FEATURE_ID_RANGE (0) 6301^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 6302 6303The Feature ID range is defined as the AArch64 System register space with 6304op0==3, op1=={0, 1, 3}, CRn==0, CRm=={0-7}, op2=={0-7}. 6305 6306The mask returned array pointed to by ``addr`` is indexed by the macro 6307``ARM64_FEATURE_ID_RANGE_IDX(op0, op1, crn, crm, op2)``, allowing userspace 6308to know what fields can be changed for the system register described by 6309``op0, op1, crn, crm, op2``. KVM rejects ID register values that describe a 6310superset of the features supported by the system. 6311 63124.140 KVM_SET_USER_MEMORY_REGION2 6313--------------------------------- 6314 6315:Capability: KVM_CAP_USER_MEMORY2 6316:Architectures: all 6317:Type: vm ioctl 6318:Parameters: struct kvm_userspace_memory_region2 (in) 6319:Returns: 0 on success, -1 on error 6320 6321KVM_SET_USER_MEMORY_REGION2 is an extension to KVM_SET_USER_MEMORY_REGION that 6322allows mapping guest_memfd memory into a guest. All fields shared with 6323KVM_SET_USER_MEMORY_REGION identically. Userspace can set KVM_MEM_GUEST_MEMFD 6324in flags to have KVM bind the memory region to a given guest_memfd range of 6325[guest_memfd_offset, guest_memfd_offset + memory_size]. The target guest_memfd 6326must point at a file created via KVM_CREATE_GUEST_MEMFD on the current VM, and 6327the target range must not be bound to any other memory region. All standard 6328bounds checks apply (use common sense). 6329 6330:: 6331 6332 struct kvm_userspace_memory_region2 { 6333 __u32 slot; 6334 __u32 flags; 6335 __u64 guest_phys_addr; 6336 __u64 memory_size; /* bytes */ 6337 __u64 userspace_addr; /* start of the userspace allocated memory */ 6338 __u64 guest_memfd_offset; 6339 __u32 guest_memfd; 6340 __u32 pad1; 6341 __u64 pad2[14]; 6342 }; 6343 6344A KVM_MEM_GUEST_MEMFD region _must_ have a valid guest_memfd (private memory) and 6345userspace_addr (shared memory). However, "valid" for userspace_addr simply 6346means that the address itself must be a legal userspace address. The backing 6347mapping for userspace_addr is not required to be valid/populated at the time of 6348KVM_SET_USER_MEMORY_REGION2, e.g. shared memory can be lazily mapped/allocated 6349on-demand. 6350 6351When mapping a gfn into the guest, KVM selects shared vs. private, i.e consumes 6352userspace_addr vs. guest_memfd, based on the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE 6353state. At VM creation time, all memory is shared, i.e. the PRIVATE attribute 6354is '0' for all gfns. Userspace can control whether memory is shared/private by 6355toggling KVM_MEMORY_ATTRIBUTE_PRIVATE via KVM_SET_MEMORY_ATTRIBUTES as needed. 6356 6357S390: 6358^^^^^ 6359 6360Returns -EINVAL if the VM has the KVM_VM_S390_UCONTROL flag set. 6361Returns -EINVAL if called on a protected VM. 6362 63634.141 KVM_SET_MEMORY_ATTRIBUTES 6364------------------------------- 6365 6366:Capability: KVM_CAP_MEMORY_ATTRIBUTES 6367:Architectures: x86 6368:Type: vm ioctl 6369:Parameters: struct kvm_memory_attributes (in) 6370:Returns: 0 on success, <0 on error 6371 6372KVM_SET_MEMORY_ATTRIBUTES allows userspace to set memory attributes for a range 6373of guest physical memory. 6374 6375:: 6376 6377 struct kvm_memory_attributes { 6378 __u64 address; 6379 __u64 size; 6380 __u64 attributes; 6381 __u64 flags; 6382 }; 6383 6384 #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) 6385 6386The address and size must be page aligned. The supported attributes can be 6387retrieved via ioctl(KVM_CHECK_EXTENSION) on KVM_CAP_MEMORY_ATTRIBUTES. If 6388executed on a VM, KVM_CAP_MEMORY_ATTRIBUTES precisely returns the attributes 6389supported by that VM. If executed at system scope, KVM_CAP_MEMORY_ATTRIBUTES 6390returns all attributes supported by KVM. The only attribute defined at this 6391time is KVM_MEMORY_ATTRIBUTE_PRIVATE, which marks the associated gfn as being 6392guest private memory. 6393 6394Note, there is no "get" API. Userspace is responsible for explicitly tracking 6395the state of a gfn/page as needed. 6396 6397The "flags" field is reserved for future extensions and must be '0'. 6398 63994.142 KVM_CREATE_GUEST_MEMFD 6400---------------------------- 6401 6402:Capability: KVM_CAP_GUEST_MEMFD 6403:Architectures: none 6404:Type: vm ioctl 6405:Parameters: struct kvm_create_guest_memfd(in) 6406:Returns: A file descriptor on success, <0 on error 6407 6408KVM_CREATE_GUEST_MEMFD creates an anonymous file and returns a file descriptor 6409that refers to it. guest_memfd files are roughly analogous to files created 6410via memfd_create(), e.g. guest_memfd files live in RAM, have volatile storage, 6411and are automatically released when the last reference is dropped. Unlike 6412"regular" memfd_create() files, guest_memfd files are bound to their owning 6413virtual machine (see below), cannot be mapped, read, or written by userspace, 6414and cannot be resized (guest_memfd files do however support PUNCH_HOLE). 6415 6416:: 6417 6418 struct kvm_create_guest_memfd { 6419 __u64 size; 6420 __u64 flags; 6421 __u64 reserved[6]; 6422 }; 6423 6424Conceptually, the inode backing a guest_memfd file represents physical memory, 6425i.e. is coupled to the virtual machine as a thing, not to a "struct kvm". The 6426file itself, which is bound to a "struct kvm", is that instance's view of the 6427underlying memory, e.g. effectively provides the translation of guest addresses 6428to host memory. This allows for use cases where multiple KVM structures are 6429used to manage a single virtual machine, e.g. when performing intrahost 6430migration of a virtual machine. 6431 6432KVM currently only supports mapping guest_memfd via KVM_SET_USER_MEMORY_REGION2, 6433and more specifically via the guest_memfd and guest_memfd_offset fields in 6434"struct kvm_userspace_memory_region2", where guest_memfd_offset is the offset 6435into the guest_memfd instance. For a given guest_memfd file, there can be at 6436most one mapping per page, i.e. binding multiple memory regions to a single 6437guest_memfd range is not allowed (any number of memory regions can be bound to 6438a single guest_memfd file, but the bound ranges must not overlap). 6439 6440The capability KVM_CAP_GUEST_MEMFD_FLAGS enumerates the `flags` that can be 6441specified via KVM_CREATE_GUEST_MEMFD. Currently defined flags: 6442 6443 ============================ ================================================ 6444 GUEST_MEMFD_FLAG_MMAP Enable using mmap() on the guest_memfd file 6445 descriptor. 6446 GUEST_MEMFD_FLAG_INIT_SHARED Make all memory in the file shared during 6447 KVM_CREATE_GUEST_MEMFD (memory files created 6448 without INIT_SHARED will be marked private). 6449 Shared memory can be faulted into host userspace 6450 page tables. Private memory cannot. 6451 ============================ ================================================ 6452 6453When the KVM MMU performs a PFN lookup to service a guest fault and the backing 6454guest_memfd has the GUEST_MEMFD_FLAG_MMAP set, then the fault will always be 6455consumed from guest_memfd, regardless of whether it is a shared or a private 6456fault. 6457 6458See KVM_SET_USER_MEMORY_REGION2 for additional details. 6459 64604.143 KVM_PRE_FAULT_MEMORY 6461--------------------------- 6462 6463:Capability: KVM_CAP_PRE_FAULT_MEMORY 6464:Architectures: none 6465:Type: vcpu ioctl 6466:Parameters: struct kvm_pre_fault_memory (in/out) 6467:Returns: 0 if at least one page is processed, < 0 on error 6468 6469Errors: 6470 6471 ========== =============================================================== 6472 EINVAL The specified `gpa` and `size` were invalid (e.g. not 6473 page aligned, causes an overflow, or size is zero). 6474 ENOENT The specified `gpa` is outside defined memslots. 6475 EINTR An unmasked signal is pending and no page was processed. 6476 EFAULT The parameter address was invalid. 6477 EOPNOTSUPP Mapping memory for a GPA is unsupported by the 6478 hypervisor, and/or for the current vCPU state/mode. 6479 EIO unexpected error conditions (also causes a WARN) 6480 ========== =============================================================== 6481 6482:: 6483 6484 struct kvm_pre_fault_memory { 6485 /* in/out */ 6486 __u64 gpa; 6487 __u64 size; 6488 /* in */ 6489 __u64 flags; 6490 __u64 padding[5]; 6491 }; 6492 6493KVM_PRE_FAULT_MEMORY populates KVM's stage-2 page tables used to map memory 6494for the current vCPU state. KVM maps memory as if the vCPU generated a 6495stage-2 read page fault, e.g. faults in memory as needed, but doesn't break 6496CoW. However, KVM does not mark any newly created stage-2 PTE as Accessed. 6497 6498In the case of confidential VM types where there is an initial set up of 6499private guest memory before the guest is 'finalized'/measured, this ioctl 6500should only be issued after completing all the necessary setup to put the 6501guest into a 'finalized' state so that the above semantics can be reliably 6502ensured. 6503 6504In some cases, multiple vCPUs might share the page tables. In this 6505case, the ioctl can be called in parallel. 6506 6507When the ioctl returns, the input values are updated to point to the 6508remaining range. If `size` > 0 on return, the caller can just issue 6509the ioctl again with the same `struct kvm_map_memory` argument. 6510 6511Shadow page tables cannot support this ioctl because they 6512are indexed by virtual address or nested guest physical address. 6513Calling this ioctl when the guest is using shadow page tables (for 6514example because it is running a nested guest with nested page tables) 6515will fail with `EOPNOTSUPP` even if `KVM_CHECK_EXTENSION` reports 6516the capability to be present. 6517 6518`flags` must currently be zero. 6519 6520 6521.. _kvm_run: 6522 65235. The kvm_run structure 6524======================== 6525 6526Application code obtains a pointer to the kvm_run structure by 6527mmap()ing a vcpu fd. From that point, application code can control 6528execution by changing fields in kvm_run prior to calling the KVM_RUN 6529ioctl, and obtain information about the reason KVM_RUN returned by 6530looking up structure members. 6531 6532:: 6533 6534 struct kvm_run { 6535 /* in */ 6536 __u8 request_interrupt_window; 6537 6538Request that KVM_RUN return when it becomes possible to inject external 6539interrupts into the guest. Useful in conjunction with KVM_INTERRUPT. 6540 6541:: 6542 6543 __u8 immediate_exit; 6544 6545This field is polled once when KVM_RUN starts; if non-zero, KVM_RUN 6546exits immediately, returning -EINTR. In the common scenario where a 6547signal is used to "kick" a VCPU out of KVM_RUN, this field can be used 6548to avoid usage of KVM_SET_SIGNAL_MASK, which has worse scalability. 6549Rather than blocking the signal outside KVM_RUN, userspace can set up 6550a signal handler that sets run->immediate_exit to a non-zero value. 6551 6552This field is ignored if KVM_CAP_IMMEDIATE_EXIT is not available. 6553 6554:: 6555 6556 __u8 padding1[6]; 6557 6558 /* out */ 6559 __u32 exit_reason; 6560 6561When KVM_RUN has returned successfully (return value 0), this informs 6562application code why KVM_RUN has returned. Allowable values for this 6563field are detailed below. 6564 6565:: 6566 6567 __u8 ready_for_interrupt_injection; 6568 6569If request_interrupt_window has been specified, this field indicates 6570an interrupt can be injected now with KVM_INTERRUPT. 6571 6572:: 6573 6574 __u8 if_flag; 6575 6576The value of the current interrupt flag. Only valid if in-kernel 6577local APIC is not used. 6578 6579:: 6580 6581 __u16 flags; 6582 6583More architecture-specific flags detailing state of the VCPU that may 6584affect the device's behavior. Current defined flags:: 6585 6586 /* x86, set if the VCPU is in system management mode */ 6587 #define KVM_RUN_X86_SMM (1 << 0) 6588 /* x86, set if bus lock detected in VM */ 6589 #define KVM_RUN_X86_BUS_LOCK (1 << 1) 6590 /* x86, set if the VCPU is executing a nested (L2) guest */ 6591 #define KVM_RUN_X86_GUEST_MODE (1 << 2) 6592 6593 /* arm64, set for KVM_EXIT_DEBUG */ 6594 #define KVM_DEBUG_ARCH_HSR_HIGH_VALID (1 << 0) 6595 6596:: 6597 6598 /* in (pre_kvm_run), out (post_kvm_run) */ 6599 __u64 cr8; 6600 6601The value of the cr8 register. Only valid if in-kernel local APIC is 6602not used. Both input and output. 6603 6604:: 6605 6606 __u64 apic_base; 6607 6608The value of the APIC BASE msr. Only valid if in-kernel local 6609APIC is not used. Both input and output. 6610 6611:: 6612 6613 union { 6614 /* KVM_EXIT_UNKNOWN */ 6615 struct { 6616 __u64 hardware_exit_reason; 6617 } hw; 6618 6619If exit_reason is KVM_EXIT_UNKNOWN, the vcpu has exited due to unknown 6620reasons. Further architecture-specific information is available in 6621hardware_exit_reason. 6622 6623:: 6624 6625 /* KVM_EXIT_FAIL_ENTRY */ 6626 struct { 6627 __u64 hardware_entry_failure_reason; 6628 __u32 cpu; /* if KVM_LAST_CPU */ 6629 } fail_entry; 6630 6631If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due 6632to unknown reasons. Further architecture-specific information is 6633available in hardware_entry_failure_reason. 6634 6635:: 6636 6637 /* KVM_EXIT_EXCEPTION */ 6638 struct { 6639 __u32 exception; 6640 __u32 error_code; 6641 } ex; 6642 6643Unused. 6644 6645:: 6646 6647 /* KVM_EXIT_IO */ 6648 struct { 6649 #define KVM_EXIT_IO_IN 0 6650 #define KVM_EXIT_IO_OUT 1 6651 __u8 direction; 6652 __u8 size; /* bytes */ 6653 __u16 port; 6654 __u32 count; 6655 __u64 data_offset; /* relative to kvm_run start */ 6656 } io; 6657 6658If exit_reason is KVM_EXIT_IO, then the vcpu has 6659executed a port I/O instruction which could not be satisfied by kvm. 6660data_offset describes where the data is located (KVM_EXIT_IO_OUT) or 6661where kvm expects application code to place the data for the next 6662KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array. 6663 6664:: 6665 6666 /* KVM_EXIT_DEBUG */ 6667 struct { 6668 struct kvm_debug_exit_arch arch; 6669 } debug; 6670 6671If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event 6672for which architecture specific information is returned. 6673 6674:: 6675 6676 /* KVM_EXIT_MMIO */ 6677 struct { 6678 __u64 phys_addr; 6679 __u8 data[8]; 6680 __u32 len; 6681 __u8 is_write; 6682 } mmio; 6683 6684If exit_reason is KVM_EXIT_MMIO, then the vcpu has 6685executed a memory-mapped I/O instruction which could not be satisfied 6686by kvm. The 'data' member contains the written data if 'is_write' is 6687true, and should be filled by application code otherwise. 6688 6689The 'data' member contains, in its first 'len' bytes, the value as it would 6690appear if the VCPU performed a load or store of the appropriate width directly 6691to the byte array. 6692 6693.. note:: 6694 6695 For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR, KVM_EXIT_XEN, 6696 KVM_EXIT_EPR, KVM_EXIT_HYPERCALL, KVM_EXIT_TDX, 6697 KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR the corresponding 6698 operations are complete (and guest state is consistent) only after userspace 6699 has re-entered the kernel with KVM_RUN. The kernel side will first finish 6700 incomplete operations and then check for pending signals. 6701 6702 The pending state of the operation is not preserved in state which is 6703 visible to userspace, thus userspace should ensure that the operation is 6704 completed before performing a live migration. Userspace can re-enter the 6705 guest with an unmasked signal pending or with the immediate_exit field set 6706 to complete pending operations without allowing any further instructions 6707 to be executed. 6708 6709:: 6710 6711 /* KVM_EXIT_HYPERCALL */ 6712 struct { 6713 __u64 nr; 6714 __u64 args[6]; 6715 __u64 ret; 6716 __u64 flags; 6717 } hypercall; 6718 6719 6720It is strongly recommended that userspace use ``KVM_EXIT_IO`` (x86) or 6721``KVM_EXIT_MMIO`` (all except s390) to implement functionality that 6722requires a guest to interact with host userspace. 6723 6724.. note:: KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO. 6725 6726For arm64: 6727---------- 6728 6729SMCCC exits can be enabled depending on the configuration of the SMCCC 6730filter. See the Documentation/virt/kvm/devices/vm.rst 6731``KVM_ARM_SMCCC_FILTER`` for more details. 6732 6733``nr`` contains the function ID of the guest's SMCCC call. Userspace is 6734expected to use the ``KVM_GET_ONE_REG`` ioctl to retrieve the call 6735parameters from the vCPU's GPRs. 6736 6737Definition of ``flags``: 6738 - ``KVM_HYPERCALL_EXIT_SMC``: Indicates that the guest used the SMC 6739 conduit to initiate the SMCCC call. If this bit is 0 then the guest 6740 used the HVC conduit for the SMCCC call. 6741 6742 - ``KVM_HYPERCALL_EXIT_16BIT``: Indicates that the guest used a 16bit 6743 instruction to initiate the SMCCC call. If this bit is 0 then the 6744 guest used a 32bit instruction. An AArch64 guest always has this 6745 bit set to 0. 6746 6747At the point of exit, PC points to the instruction immediately following 6748the trapping instruction. 6749 6750:: 6751 6752 /* KVM_EXIT_TPR_ACCESS */ 6753 struct { 6754 __u64 rip; 6755 __u32 is_write; 6756 __u32 pad; 6757 } tpr_access; 6758 6759To be documented (KVM_TPR_ACCESS_REPORTING). 6760 6761:: 6762 6763 /* KVM_EXIT_S390_SIEIC */ 6764 struct { 6765 __u8 icptcode; 6766 __u64 mask; /* psw upper half */ 6767 __u64 addr; /* psw lower half */ 6768 __u16 ipa; 6769 __u32 ipb; 6770 } s390_sieic; 6771 6772s390 specific. 6773 6774:: 6775 6776 /* KVM_EXIT_S390_RESET */ 6777 #define KVM_S390_RESET_POR 1 6778 #define KVM_S390_RESET_CLEAR 2 6779 #define KVM_S390_RESET_SUBSYSTEM 4 6780 #define KVM_S390_RESET_CPU_INIT 8 6781 #define KVM_S390_RESET_IPL 16 6782 __u64 s390_reset_flags; 6783 6784s390 specific. 6785 6786:: 6787 6788 /* KVM_EXIT_S390_UCONTROL */ 6789 struct { 6790 __u64 trans_exc_code; 6791 __u32 pgm_code; 6792 } s390_ucontrol; 6793 6794s390 specific. A page fault has occurred for a user controlled virtual 6795machine (KVM_VM_S390_UNCONTROL) on its host page table that cannot be 6796resolved by the kernel. 6797The program code and the translation exception code that were placed 6798in the cpu's lowcore are presented here as defined by the z Architecture 6799Principles of Operation Book in the Chapter for Dynamic Address Translation 6800(DAT) 6801 6802:: 6803 6804 /* KVM_EXIT_DCR */ 6805 struct { 6806 __u32 dcrn; 6807 __u32 data; 6808 __u8 is_write; 6809 } dcr; 6810 6811Deprecated - was used for 440 KVM. 6812 6813:: 6814 6815 /* KVM_EXIT_OSI */ 6816 struct { 6817 __u64 gprs[32]; 6818 } osi; 6819 6820MOL uses a special hypercall interface it calls 'OSI'. To enable it, we catch 6821hypercalls and exit with this exit struct that contains all the guest gprs. 6822 6823If exit_reason is KVM_EXIT_OSI, then the vcpu has triggered such a hypercall. 6824Userspace can now handle the hypercall and when it's done modify the gprs as 6825necessary. Upon guest entry all guest GPRs will then be replaced by the values 6826in this struct. 6827 6828:: 6829 6830 /* KVM_EXIT_PAPR_HCALL */ 6831 struct { 6832 __u64 nr; 6833 __u64 ret; 6834 __u64 args[9]; 6835 } papr_hcall; 6836 6837This is used on 64-bit PowerPC when emulating a pSeries partition, 6838e.g. with the 'pseries' machine type in qemu. It occurs when the 6839guest does a hypercall using the 'sc 1' instruction. The 'nr' field 6840contains the hypercall number (from the guest R3), and 'args' contains 6841the arguments (from the guest R4 - R12). Userspace should put the 6842return code in 'ret' and any extra returned values in args[]. 6843The possible hypercalls are defined in the Power Architecture Platform 6844Requirements (PAPR) document available from www.power.org (free 6845developer registration required to access it). 6846 6847:: 6848 6849 /* KVM_EXIT_S390_TSCH */ 6850 struct { 6851 __u16 subchannel_id; 6852 __u16 subchannel_nr; 6853 __u32 io_int_parm; 6854 __u32 io_int_word; 6855 __u32 ipb; 6856 __u8 dequeued; 6857 } s390_tsch; 6858 6859s390 specific. This exit occurs when KVM_CAP_S390_CSS_SUPPORT has been enabled 6860and TEST SUBCHANNEL was intercepted. If dequeued is set, a pending I/O 6861interrupt for the target subchannel has been dequeued and subchannel_id, 6862subchannel_nr, io_int_parm and io_int_word contain the parameters for that 6863interrupt. ipb is needed for instruction parameter decoding. 6864 6865:: 6866 6867 /* KVM_EXIT_EPR */ 6868 struct { 6869 __u32 epr; 6870 } epr; 6871 6872On FSL BookE PowerPC chips, the interrupt controller has a fast patch 6873interrupt acknowledge path to the core. When the core successfully 6874delivers an interrupt, it automatically populates the EPR register with 6875the interrupt vector number and acknowledges the interrupt inside 6876the interrupt controller. 6877 6878In case the interrupt controller lives in user space, we need to do 6879the interrupt acknowledge cycle through it to fetch the next to be 6880delivered interrupt vector using this exit. 6881 6882It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an 6883external interrupt has just been delivered into the guest. User space 6884should put the acknowledged interrupt vector into the 'epr' field. 6885 6886:: 6887 6888 /* KVM_EXIT_SYSTEM_EVENT */ 6889 struct { 6890 #define KVM_SYSTEM_EVENT_SHUTDOWN 1 6891 #define KVM_SYSTEM_EVENT_RESET 2 6892 #define KVM_SYSTEM_EVENT_CRASH 3 6893 #define KVM_SYSTEM_EVENT_WAKEUP 4 6894 #define KVM_SYSTEM_EVENT_SUSPEND 5 6895 #define KVM_SYSTEM_EVENT_SEV_TERM 6 6896 #define KVM_SYSTEM_EVENT_TDX_FATAL 7 6897 __u32 type; 6898 __u32 ndata; 6899 __u64 data[16]; 6900 } system_event; 6901 6902If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered 6903a system-level event using some architecture specific mechanism (hypercall 6904or some special instruction). In case of ARM64, this is triggered using 6905HVC instruction based PSCI call from the vcpu. 6906 6907The 'type' field describes the system-level event type. 6908Valid values for 'type' are: 6909 6910 - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the 6911 VM. Userspace is not obliged to honour this, and if it does honour 6912 this does not need to destroy the VM synchronously (ie it may call 6913 KVM_RUN again before shutdown finally occurs). 6914 - KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM. 6915 As with SHUTDOWN, userspace can choose to ignore the request, or 6916 to schedule the reset to occur in the future and may call KVM_RUN again. 6917 - KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest 6918 has requested a crash condition maintenance. Userspace can choose 6919 to ignore the request, or to gather VM memory core dump and/or 6920 reset/shutdown of the VM. 6921 - KVM_SYSTEM_EVENT_SEV_TERM -- an AMD SEV guest requested termination. 6922 The guest physical address of the guest's GHCB is stored in `data[0]`. 6923 - KVM_SYSTEM_EVENT_TDX_FATAL -- a TDX guest reported a fatal error state. 6924 KVM doesn't do any parsing or conversion, it just dumps 16 general-purpose 6925 registers to userspace, in ascending order of the 4-bit indices for x86-64 6926 general-purpose registers in instruction encoding, as defined in the Intel 6927 SDM. 6928 - KVM_SYSTEM_EVENT_WAKEUP -- the exiting vCPU is in a suspended state and 6929 KVM has recognized a wakeup event. Userspace may honor this event by 6930 marking the exiting vCPU as runnable, or deny it and call KVM_RUN again. 6931 - KVM_SYSTEM_EVENT_SUSPEND -- the guest has requested a suspension of 6932 the VM. 6933 6934If KVM_CAP_SYSTEM_EVENT_DATA is present, the 'data' field can contain 6935architecture specific information for the system-level event. Only 6936the first `ndata` items (possibly zero) of the data array are valid. 6937 6938 - for arm64, data[0] is set to KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 if 6939 the guest issued a SYSTEM_RESET2 call according to v1.1 of the PSCI 6940 specification. 6941 6942 - for arm64, data[0] is set to KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2 6943 if the guest issued a SYSTEM_OFF2 call according to v1.3 of the PSCI 6944 specification. 6945 6946 - for RISC-V, data[0] is set to the value of the second argument of the 6947 ``sbi_system_reset`` call. 6948 6949Previous versions of Linux defined a `flags` member in this struct. The 6950field is now aliased to `data[0]`. Userspace can assume that it is only 6951written if ndata is greater than 0. 6952 6953For arm/arm64: 6954-------------- 6955 6956KVM_SYSTEM_EVENT_SUSPEND exits are enabled with the 6957KVM_CAP_ARM_SYSTEM_SUSPEND VM capability. If a guest invokes the PSCI 6958SYSTEM_SUSPEND function, KVM will exit to userspace with this event 6959type. 6960 6961It is the sole responsibility of userspace to implement the PSCI 6962SYSTEM_SUSPEND call according to ARM DEN0022D.b 5.19 "SYSTEM_SUSPEND". 6963KVM does not change the vCPU's state before exiting to userspace, so 6964the call parameters are left in-place in the vCPU registers. 6965 6966Userspace is _required_ to take action for such an exit. It must 6967either: 6968 6969 - Honor the guest request to suspend the VM. Userspace can request 6970 in-kernel emulation of suspension by setting the calling vCPU's 6971 state to KVM_MP_STATE_SUSPENDED. Userspace must configure the vCPU's 6972 state according to the parameters passed to the PSCI function when 6973 the calling vCPU is resumed. See ARM DEN0022D.b 5.19.1 "Intended use" 6974 for details on the function parameters. 6975 6976 - Deny the guest request to suspend the VM. See ARM DEN0022D.b 5.19.2 6977 "Caller responsibilities" for possible return values. 6978 6979Hibernation using the PSCI SYSTEM_OFF2 call is enabled when PSCI v1.3 6980is enabled. If a guest invokes the PSCI SYSTEM_OFF2 function, KVM will 6981exit to userspace with the KVM_SYSTEM_EVENT_SHUTDOWN event type and with 6982data[0] set to KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2. The only 6983supported hibernate type for the SYSTEM_OFF2 function is HIBERNATE_OFF. 6984 6985:: 6986 6987 /* KVM_EXIT_IOAPIC_EOI */ 6988 struct { 6989 __u8 vector; 6990 } eoi; 6991 6992Indicates that the VCPU's in-kernel local APIC received an EOI for a 6993level-triggered IOAPIC interrupt. This exit only triggers when the 6994IOAPIC is implemented in userspace (i.e. KVM_CAP_SPLIT_IRQCHIP is enabled); 6995the userspace IOAPIC should process the EOI and retrigger the interrupt if 6996it is still asserted. Vector is the LAPIC interrupt vector for which the 6997EOI was received. 6998 6999:: 7000 7001 struct kvm_hyperv_exit { 7002 #define KVM_EXIT_HYPERV_SYNIC 1 7003 #define KVM_EXIT_HYPERV_HCALL 2 7004 #define KVM_EXIT_HYPERV_SYNDBG 3 7005 __u32 type; 7006 __u32 pad1; 7007 union { 7008 struct { 7009 __u32 msr; 7010 __u32 pad2; 7011 __u64 control; 7012 __u64 evt_page; 7013 __u64 msg_page; 7014 } synic; 7015 struct { 7016 __u64 input; 7017 __u64 result; 7018 __u64 params[2]; 7019 } hcall; 7020 struct { 7021 __u32 msr; 7022 __u32 pad2; 7023 __u64 control; 7024 __u64 status; 7025 __u64 send_page; 7026 __u64 recv_page; 7027 __u64 pending_page; 7028 } syndbg; 7029 } u; 7030 }; 7031 /* KVM_EXIT_HYPERV */ 7032 struct kvm_hyperv_exit hyperv; 7033 7034Indicates that the VCPU exits into userspace to process some tasks 7035related to Hyper-V emulation. 7036 7037Valid values for 'type' are: 7038 7039 - KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about 7040 7041Hyper-V SynIC state change. Notification is used to remap SynIC 7042event/message pages and to enable/disable SynIC messages/events processing 7043in userspace. 7044 7045 - KVM_EXIT_HYPERV_SYNDBG -- synchronously notify user-space about 7046 7047Hyper-V Synthetic debugger state change. Notification is used to either update 7048the pending_page location or to send a control command (send the buffer located 7049in send_page or recv a buffer to recv_page). 7050 7051:: 7052 7053 /* KVM_EXIT_ARM_NISV */ 7054 struct { 7055 __u64 esr_iss; 7056 __u64 fault_ipa; 7057 } arm_nisv; 7058 7059Used on arm64 systems. If a guest accesses memory not in a memslot, 7060KVM will typically return to userspace and ask it to do MMIO emulation on its 7061behalf. However, for certain classes of instructions, no instruction decode 7062(direction, length of memory access) is provided, and fetching and decoding 7063the instruction from the VM is overly complicated to live in the kernel. 7064 7065Historically, when this situation occurred, KVM would print a warning and kill 7066the VM. KVM assumed that if the guest accessed non-memslot memory, it was 7067trying to do I/O, which just couldn't be emulated, and the warning message was 7068phrased accordingly. However, what happened more often was that a guest bug 7069caused access outside the guest memory areas which should lead to a more 7070meaningful warning message and an external abort in the guest, if the access 7071did not fall within an I/O window. 7072 7073Userspace implementations can query for KVM_CAP_ARM_NISV_TO_USER, and enable 7074this capability at VM creation. Once this is done, these types of errors will 7075instead return to userspace with KVM_EXIT_ARM_NISV, with the valid bits from 7076the ESR_EL2 in the esr_iss field, and the faulting IPA in the fault_ipa field. 7077Userspace can either fix up the access if it's actually an I/O access by 7078decoding the instruction from guest memory (if it's very brave) and continue 7079executing the guest, or it can decide to suspend, dump, or restart the guest. 7080 7081Note that KVM does not skip the faulting instruction as it does for 7082KVM_EXIT_MMIO, but userspace has to emulate any change to the processing state 7083if it decides to decode and emulate the instruction. 7084 7085This feature isn't available to protected VMs, as userspace does not 7086have access to the state that is required to perform the emulation. 7087Instead, a data abort exception is directly injected in the guest. 7088Note that although KVM_CAP_ARM_NISV_TO_USER will be reported if 7089queried outside of a protected VM context, the feature will not be 7090exposed if queried on a protected VM file descriptor. 7091 7092:: 7093 7094 /* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */ 7095 struct { 7096 __u8 error; /* user -> kernel */ 7097 __u8 pad[7]; 7098 __u32 reason; /* kernel -> user */ 7099 __u32 index; /* kernel -> user */ 7100 __u64 data; /* kernel <-> user */ 7101 } msr; 7102 7103Used on x86 systems. When the VM capability KVM_CAP_X86_USER_SPACE_MSR is 7104enabled, MSR accesses to registers that would invoke a #GP by KVM kernel code 7105may instead trigger a KVM_EXIT_X86_RDMSR exit for reads and KVM_EXIT_X86_WRMSR 7106exit for writes. 7107 7108The "reason" field specifies why the MSR interception occurred. Userspace will 7109only receive MSR exits when a particular reason was requested during through 7110ENABLE_CAP. Currently valid exit reasons are: 7111 7112============================ ======================================== 7113 KVM_MSR_EXIT_REASON_UNKNOWN access to MSR that is unknown to KVM 7114 KVM_MSR_EXIT_REASON_INVAL access to invalid MSRs or reserved bits 7115 KVM_MSR_EXIT_REASON_FILTER access blocked by KVM_X86_SET_MSR_FILTER 7116============================ ======================================== 7117 7118For KVM_EXIT_X86_RDMSR, the "index" field tells userspace which MSR the guest 7119wants to read. To respond to this request with a successful read, userspace 7120writes the respective data into the "data" field and must continue guest 7121execution to ensure the read data is transferred into guest register state. 7122 7123If the RDMSR request was unsuccessful, userspace indicates that with a "1" in 7124the "error" field. This will inject a #GP into the guest when the VCPU is 7125executed again. 7126 7127For KVM_EXIT_X86_WRMSR, the "index" field tells userspace which MSR the guest 7128wants to write. Once finished processing the event, userspace must continue 7129vCPU execution. If the MSR write was unsuccessful, userspace also sets the 7130"error" field to "1". 7131 7132See KVM_X86_SET_MSR_FILTER for details on the interaction with MSR filtering. 7133 7134:: 7135 7136 7137 struct kvm_xen_exit { 7138 #define KVM_EXIT_XEN_HCALL 1 7139 __u32 type; 7140 union { 7141 struct { 7142 __u32 longmode; 7143 __u32 cpl; 7144 __u64 input; 7145 __u64 result; 7146 __u64 params[6]; 7147 } hcall; 7148 } u; 7149 }; 7150 /* KVM_EXIT_XEN */ 7151 struct kvm_hyperv_exit xen; 7152 7153Indicates that the VCPU exits into userspace to process some tasks 7154related to Xen emulation. 7155 7156Valid values for 'type' are: 7157 7158 - KVM_EXIT_XEN_HCALL -- synchronously notify user-space about Xen hypercall. 7159 Userspace is expected to place the hypercall result into the appropriate 7160 field before invoking KVM_RUN again. 7161 7162:: 7163 7164 /* KVM_EXIT_RISCV_SBI */ 7165 struct { 7166 unsigned long extension_id; 7167 unsigned long function_id; 7168 unsigned long args[6]; 7169 unsigned long ret[2]; 7170 } riscv_sbi; 7171 7172If exit reason is KVM_EXIT_RISCV_SBI then it indicates that the VCPU has 7173done a SBI call which is not handled by KVM RISC-V kernel module. The details 7174of the SBI call are available in 'riscv_sbi' member of kvm_run structure. The 7175'extension_id' field of 'riscv_sbi' represents SBI extension ID whereas the 7176'function_id' field represents function ID of given SBI extension. The 'args' 7177array field of 'riscv_sbi' represents parameters for the SBI call and 'ret' 7178array field represents return values. The userspace should update the return 7179values of SBI call before resuming the VCPU. For more details on RISC-V SBI 7180spec refer, https://github.com/riscv/riscv-sbi-doc. 7181 7182:: 7183 7184 /* KVM_EXIT_MEMORY_FAULT */ 7185 struct { 7186 #define KVM_MEMORY_EXIT_FLAG_PRIVATE (1ULL << 3) 7187 __u64 flags; 7188 __u64 gpa; 7189 __u64 size; 7190 } memory_fault; 7191 7192KVM_EXIT_MEMORY_FAULT indicates the vCPU has encountered a memory fault that 7193could not be resolved by KVM. The 'gpa' and 'size' (in bytes) describe the 7194guest physical address range [gpa, gpa + size) of the fault. The 'flags' field 7195describes properties of the faulting access that are likely pertinent: 7196 7197 - KVM_MEMORY_EXIT_FLAG_PRIVATE - When set, indicates the memory fault occurred 7198 on a private memory access. When clear, indicates the fault occurred on a 7199 shared access. 7200 7201Note! KVM_EXIT_MEMORY_FAULT is unique among all KVM exit reasons in that it 7202accompanies a return code of '-1', not '0'! errno will always be set to EFAULT 7203or EHWPOISON when KVM exits with KVM_EXIT_MEMORY_FAULT, userspace should assume 7204kvm_run.exit_reason is stale/undefined for all other error numbers. 7205 7206:: 7207 7208 /* KVM_EXIT_NOTIFY */ 7209 struct { 7210 #define KVM_NOTIFY_CONTEXT_INVALID (1 << 0) 7211 __u32 flags; 7212 } notify; 7213 7214Used on x86 systems. When the VM capability KVM_CAP_X86_NOTIFY_VMEXIT is 7215enabled, a VM exit generated if no event window occurs in VM non-root mode 7216for a specified amount of time. Once KVM_X86_NOTIFY_VMEXIT_USER is set when 7217enabling the cap, it would exit to userspace with the exit reason 7218KVM_EXIT_NOTIFY for further handling. The "flags" field contains more 7219detailed info. 7220 7221The valid value for 'flags' is: 7222 7223 - KVM_NOTIFY_CONTEXT_INVALID -- the VM context is corrupted and not valid 7224 in VMCS. It would run into unknown result if resume the target VM. 7225 7226:: 7227 7228 /* KVM_EXIT_TDX */ 7229 struct { 7230 __u64 flags; 7231 __u64 nr; 7232 union { 7233 struct { 7234 u64 ret; 7235 u64 data[5]; 7236 } unknown; 7237 struct { 7238 u64 ret; 7239 u64 gpa; 7240 u64 size; 7241 } get_quote; 7242 struct { 7243 u64 ret; 7244 u64 leaf; 7245 u64 r11, r12, r13, r14; 7246 } get_tdvmcall_info; 7247 struct { 7248 u64 ret; 7249 u64 vector; 7250 } setup_event_notify; 7251 }; 7252 } tdx; 7253 7254Process a TDVMCALL from the guest. KVM forwards select TDVMCALL based 7255on the Guest-Hypervisor Communication Interface (GHCI) specification; 7256KVM bridges these requests to the userspace VMM with minimal changes, 7257placing the inputs in the union and copying them back to the guest 7258on re-entry. 7259 7260Flags are currently always zero, whereas ``nr`` contains the TDVMCALL 7261number from register R11. The remaining field of the union provide the 7262inputs and outputs of the TDVMCALL. Currently the following values of 7263``nr`` are defined: 7264 7265 * ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote 7266 signed by a service hosting TD-Quoting Enclave operating on the host. 7267 Parameters and return value are in the ``get_quote`` field of the union. 7268 The ``gpa`` field and ``size`` specify the guest physical address 7269 (without the shared bit set) and the size of a shared-memory buffer, in 7270 which the TDX guest passes a TD Report. The ``ret`` field represents 7271 the return value of the GetQuote request. When the request has been 7272 queued successfully, the TDX guest can poll the status field in the 7273 shared-memory area to check whether the Quote generation is completed or 7274 not. When completed, the generated Quote is returned via the same buffer. 7275 7276 * ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support 7277 status of TDVMCALLs. The output values for the given leaf should be 7278 placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info`` 7279 field of the union. 7280 7281 * ``TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT``: the guest has requested to 7282 set up a notification interrupt for vector ``vector``. 7283 7284KVM may add support for more values in the future that may cause a userspace 7285exit, even without calls to ``KVM_ENABLE_CAP`` or similar. In this case, 7286it will enter with output fields already valid; in the common case, the 7287``unknown.ret`` field of the union will be ``TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED``. 7288Userspace need not do anything if it does not wish to support a TDVMCALL. 7289:: 7290 7291 /* Fix the size of the union. */ 7292 char padding[256]; 7293 }; 7294 7295 /* 7296 * shared registers between kvm and userspace. 7297 * kvm_valid_regs specifies the register classes set by the host 7298 * kvm_dirty_regs specified the register classes dirtied by userspace 7299 * struct kvm_sync_regs is architecture specific, as well as the 7300 * bits for kvm_valid_regs and kvm_dirty_regs 7301 */ 7302 __u64 kvm_valid_regs; 7303 __u64 kvm_dirty_regs; 7304 union { 7305 struct kvm_sync_regs regs; 7306 char padding[SYNC_REGS_SIZE_BYTES]; 7307 } s; 7308 7309If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access 7310certain guest registers without having to call SET/GET_*REGS. Thus we can 7311avoid some system call overhead if userspace has to handle the exit. 7312Userspace can query the validity of the structure by checking 7313kvm_valid_regs for specific bits. These bits are architecture specific 7314and usually define the validity of a groups of registers. (e.g. one bit 7315for general purpose registers) 7316 7317Please note that the kernel is allowed to use the kvm_run structure as the 7318primary storage for certain register types. Therefore, the kernel may use the 7319values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set. 7320 7321 7322.. _cap_enable: 7323 73246. Capabilities that can be enabled on vCPUs 7325============================================ 7326 7327There are certain capabilities that change the behavior of the virtual CPU or 7328the virtual machine when enabled. To enable them, please see 7329:ref:`KVM_ENABLE_CAP`. 7330 7331Below you can find a list of capabilities and what their effect on the vCPU or 7332the virtual machine is when enabling them. 7333 7334The following information is provided along with the description: 7335 7336 Architectures: 7337 which instruction set architectures provide this ioctl. 7338 x86 includes both i386 and x86_64. 7339 7340 Target: 7341 whether this is a per-vcpu or per-vm capability. 7342 7343 Parameters: 7344 what parameters are accepted by the capability. 7345 7346 Returns: 7347 the return value. General error numbers (EBADF, ENOMEM, EINVAL) 7348 are not detailed, but errors with specific meanings are. 7349 7350 73516.1 KVM_CAP_PPC_OSI 7352------------------- 7353 7354:Architectures: ppc 7355:Target: vcpu 7356:Parameters: none 7357:Returns: 0 on success; -1 on error 7358 7359This capability enables interception of OSI hypercalls that otherwise would 7360be treated as normal system calls to be injected into the guest. OSI hypercalls 7361were invented by Mac-on-Linux to have a standardized communication mechanism 7362between the guest and the host. 7363 7364When this capability is enabled, KVM_EXIT_OSI can occur. 7365 7366 73676.2 KVM_CAP_PPC_PAPR 7368-------------------- 7369 7370:Architectures: ppc 7371:Target: vcpu 7372:Parameters: none 7373:Returns: 0 on success; -1 on error 7374 7375This capability enables interception of PAPR hypercalls. PAPR hypercalls are 7376done using the hypercall instruction "sc 1". 7377 7378It also sets the guest privilege level to "supervisor" mode. Usually the guest 7379runs in "hypervisor" privilege mode with a few missing features. 7380 7381In addition to the above, it changes the semantics of SDR1. In this mode, the 7382HTAB address part of SDR1 contains an HVA instead of a GPA, as PAPR keeps the 7383HTAB invisible to the guest. 7384 7385When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur. 7386 7387 73886.3 KVM_CAP_SW_TLB 7389------------------ 7390 7391:Architectures: ppc 7392:Target: vcpu 7393:Parameters: args[0] is the address of a struct kvm_config_tlb 7394:Returns: 0 on success; -1 on error 7395 7396:: 7397 7398 struct kvm_config_tlb { 7399 __u64 params; 7400 __u64 array; 7401 __u32 mmu_type; 7402 __u32 array_len; 7403 }; 7404 7405Configures the virtual CPU's TLB array, establishing a shared memory area 7406between userspace and KVM. The "params" and "array" fields are userspace 7407addresses of mmu-type-specific data structures. The "array_len" field is an 7408safety mechanism, and should be set to the size in bytes of the memory that 7409userspace has reserved for the array. It must be at least the size dictated 7410by "mmu_type" and "params". 7411 7412While KVM_RUN is active, the shared region is under control of KVM. Its 7413contents are undefined, and any modification by userspace results in 7414boundedly undefined behavior. 7415 7416On return from KVM_RUN, the shared region will reflect the current state of 7417the guest's TLB. If userspace makes any changes, it must call KVM_DIRTY_TLB 7418to tell KVM which entries have been changed, prior to calling KVM_RUN again 7419on this vcpu. 7420 7421For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV: 7422 7423 - The "params" field is of type "struct kvm_book3e_206_tlb_params". 7424 - The "array" field points to an array of type "struct 7425 kvm_book3e_206_tlb_entry". 7426 - The array consists of all entries in the first TLB, followed by all 7427 entries in the second TLB. 7428 - Within a TLB, entries are ordered first by increasing set number. Within a 7429 set, entries are ordered by way (increasing ESEL). 7430 - The hash for determining set number in TLB0 is: (MAS2 >> 12) & (num_sets - 1) 7431 where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value. 7432 - The tsize field of mas1 shall be set to 4K on TLB0, even though the 7433 hardware ignores this value for TLB0. 7434 74356.4 KVM_CAP_S390_CSS_SUPPORT 7436---------------------------- 7437 7438:Architectures: s390 7439:Target: vcpu 7440:Parameters: none 7441:Returns: 0 on success; -1 on error 7442 7443This capability enables support for handling of channel I/O instructions. 7444 7445TEST PENDING INTERRUPTION and the interrupt portion of TEST SUBCHANNEL are 7446handled in-kernel, while the other I/O instructions are passed to userspace. 7447 7448When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST 7449SUBCHANNEL intercepts. 7450 7451Note that even though this capability is enabled per-vcpu, the complete 7452virtual machine is affected. 7453 74546.5 KVM_CAP_PPC_EPR 7455------------------- 7456 7457:Architectures: ppc 7458:Target: vcpu 7459:Parameters: args[0] defines whether the proxy facility is active 7460:Returns: 0 on success; -1 on error 7461 7462This capability enables or disables the delivery of interrupts through the 7463external proxy facility. 7464 7465When enabled (args[0] != 0), every time the guest gets an external interrupt 7466delivered, it automatically exits into user space with a KVM_EXIT_EPR exit 7467to receive the topmost interrupt vector. 7468 7469When disabled (args[0] == 0), behavior is as if this facility is unsupported. 7470 7471When this capability is enabled, KVM_EXIT_EPR can occur. 7472 74736.6 KVM_CAP_IRQ_MPIC 7474-------------------- 7475 7476:Architectures: ppc 7477:Parameters: args[0] is the MPIC device fd; 7478 args[1] is the MPIC CPU number for this vcpu 7479 7480This capability connects the vcpu to an in-kernel MPIC device. 7481 74826.7 KVM_CAP_IRQ_XICS 7483-------------------- 7484 7485:Architectures: ppc 7486:Target: vcpu 7487:Parameters: args[0] is the XICS device fd; 7488 args[1] is the XICS CPU number (server ID) for this vcpu 7489 7490This capability connects the vcpu to an in-kernel XICS device. 7491 74926.8 KVM_CAP_S390_IRQCHIP 7493------------------------ 7494 7495:Architectures: s390 7496:Target: vm 7497:Parameters: none 7498 7499This capability enables the in-kernel irqchip for s390. Please refer to 7500"4.24 KVM_CREATE_IRQCHIP" for details. 7501 75026.9 KVM_CAP_MIPS_FPU 7503-------------------- 7504 7505:Architectures: mips 7506:Target: vcpu 7507:Parameters: args[0] is reserved for future use (should be 0). 7508 7509This capability allows the use of the host Floating Point Unit by the guest. It 7510allows the Config1.FP bit to be set to enable the FPU in the guest. Once this is 7511done the ``KVM_REG_MIPS_FPR_*`` and ``KVM_REG_MIPS_FCR_*`` registers can be 7512accessed (depending on the current guest FPU register mode), and the Status.FR, 7513Config5.FRE bits are accessible via the KVM API and also from the guest, 7514depending on them being supported by the FPU. 7515 75166.10 KVM_CAP_MIPS_MSA 7517--------------------- 7518 7519:Architectures: mips 7520:Target: vcpu 7521:Parameters: args[0] is reserved for future use (should be 0). 7522 7523This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest. 7524It allows the Config3.MSAP bit to be set to enable the use of MSA by the guest. 7525Once this is done the ``KVM_REG_MIPS_VEC_*`` and ``KVM_REG_MIPS_MSA_*`` 7526registers can be accessed, and the Config5.MSAEn bit is accessible via the 7527KVM API and also from the guest. 7528 75296.74 KVM_CAP_SYNC_REGS 7530---------------------- 7531 7532:Architectures: s390, x86 7533:Target: s390: always enabled, x86: vcpu 7534:Parameters: none 7535:Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register 7536 sets are supported 7537 (bitfields defined in arch/x86/include/uapi/asm/kvm.h). 7538 7539As described above in the kvm_sync_regs struct info in section :ref:`kvm_run`, 7540KVM_CAP_SYNC_REGS "allow[s] userspace to access certain guest registers 7541without having to call SET/GET_*REGS". This reduces overhead by eliminating 7542repeated ioctl calls for setting and/or getting register values. This is 7543particularly important when userspace is making synchronous guest state 7544modifications, e.g. when emulating and/or intercepting instructions in 7545userspace. 7546 7547For s390 specifics, please refer to the source code. 7548 7549For x86: 7550 7551- the register sets to be copied out to kvm_run are selectable 7552 by userspace (rather that all sets being copied out for every exit). 7553- vcpu_events are available in addition to regs and sregs. 7554 7555For x86, the 'kvm_valid_regs' field of struct kvm_run is overloaded to 7556function as an input bit-array field set by userspace to indicate the 7557specific register sets to be copied out on the next exit. 7558 7559To indicate when userspace has modified values that should be copied into 7560the vCPU, the all architecture bitarray field, 'kvm_dirty_regs' must be set. 7561This is done using the same bitflags as for the 'kvm_valid_regs' field. 7562If the dirty bit is not set, then the register set values will not be copied 7563into the vCPU even if they've been modified. 7564 7565Unused bitfields in the bitarrays must be set to zero. 7566 7567:: 7568 7569 struct kvm_sync_regs { 7570 struct kvm_regs regs; 7571 struct kvm_sregs sregs; 7572 struct kvm_vcpu_events events; 7573 }; 7574 75756.75 KVM_CAP_PPC_IRQ_XIVE 7576------------------------- 7577 7578:Architectures: ppc 7579:Target: vcpu 7580:Parameters: args[0] is the XIVE device fd; 7581 args[1] is the XIVE CPU number (server ID) for this vcpu 7582 7583This capability connects the vcpu to an in-kernel XIVE device. 7584 75856.76 KVM_CAP_HYPERV_SYNIC 7586------------------------- 7587 7588:Architectures: x86 7589:Target: vcpu 7590 7591This capability, if KVM_CHECK_EXTENSION indicates that it is 7592available, means that the kernel has an implementation of the 7593Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is 7594used to support Windows Hyper-V based guest paravirt drivers(VMBus). 7595 7596In order to use SynIC, it has to be activated by setting this 7597capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this 7598will disable the use of APIC hardware virtualization even if supported 7599by the CPU, as it's incompatible with SynIC auto-EOI behavior. 7600 76016.77 KVM_CAP_HYPERV_SYNIC2 7602-------------------------- 7603 7604:Architectures: x86 7605:Target: vcpu 7606 7607This capability enables a newer version of Hyper-V Synthetic interrupt 7608controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM 7609doesn't clear SynIC message and event flags pages when they are enabled by 7610writing to the respective MSRs. 7611 76126.78 KVM_CAP_HYPERV_DIRECT_TLBFLUSH 7613----------------------------------- 7614 7615:Architectures: x86 7616:Target: vcpu 7617 7618This capability indicates that KVM running on top of Hyper-V hypervisor 7619enables Direct TLB flush for its guests meaning that TLB flush 7620hypercalls are handled by Level 0 hypervisor (Hyper-V) bypassing KVM. 7621Due to the different ABI for hypercall parameters between Hyper-V and 7622KVM, enabling this capability effectively disables all hypercall 7623handling by KVM (as some KVM hypercall may be mistakenly treated as TLB 7624flush hypercalls by Hyper-V) so userspace should disable KVM identification 7625in CPUID and only exposes Hyper-V identification. In this case, guest 7626thinks it's running on Hyper-V and only use Hyper-V hypercalls. 7627 76286.79 KVM_CAP_HYPERV_ENFORCE_CPUID 7629--------------------------------- 7630 7631:Architectures: x86 7632:Target: vcpu 7633 7634When enabled, KVM will disable emulated Hyper-V features provided to the 7635guest according to the bits Hyper-V CPUID feature leaves. Otherwise, all 7636currently implemented Hyper-V features are provided unconditionally when 7637Hyper-V identification is set in the HYPERV_CPUID_INTERFACE (0x40000001) 7638leaf. 7639 76406.80 KVM_CAP_ENFORCE_PV_FEATURE_CPUID 7641------------------------------------- 7642 7643:Architectures: x86 7644:Target: vcpu 7645 7646When enabled, KVM will disable paravirtual features provided to the 7647guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf 7648(0x40000001). Otherwise, a guest may use the paravirtual features 7649regardless of what has actually been exposed through the CPUID leaf. 7650 7651.. _KVM_CAP_DIRTY_LOG_RING: 7652 7653 7654.. _cap_enable_vm: 7655 76567. Capabilities that can be enabled on VMs 7657========================================== 7658 7659There are certain capabilities that change the behavior of the virtual 7660machine when enabled. To enable them, please see section 7661:ref:`KVM_ENABLE_CAP`. Below you can find a list of capabilities and 7662what their effect on the VM is when enabling them. 7663 7664The following information is provided along with the description: 7665 7666 Architectures: 7667 which instruction set architectures provide this ioctl. 7668 x86 includes both i386 and x86_64. 7669 7670 Parameters: 7671 what parameters are accepted by the capability. 7672 7673 Returns: 7674 the return value. General error numbers (EBADF, ENOMEM, EINVAL) 7675 are not detailed, but errors with specific meanings are. 7676 7677 76787.1 KVM_CAP_PPC_ENABLE_HCALL 7679---------------------------- 7680 7681:Architectures: ppc 7682:Parameters: args[0] is the sPAPR hcall number; 7683 args[1] is 0 to disable, 1 to enable in-kernel handling 7684 7685This capability controls whether individual sPAPR hypercalls (hcalls) 7686get handled by the kernel or not. Enabling or disabling in-kernel 7687handling of an hcall is effective across the VM. On creation, an 7688initial set of hcalls are enabled for in-kernel handling, which 7689consists of those hcalls for which in-kernel handlers were implemented 7690before this capability was implemented. If disabled, the kernel will 7691not to attempt to handle the hcall, but will always exit to userspace 7692to handle it. Note that it may not make sense to enable some and 7693disable others of a group of related hcalls, but KVM does not prevent 7694userspace from doing that. 7695 7696If the hcall number specified is not one that has an in-kernel 7697implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL 7698error. 7699 77007.2 KVM_CAP_S390_USER_SIGP 7701-------------------------- 7702 7703:Architectures: s390 7704:Parameters: none 7705 7706This capability controls which SIGP orders will be handled completely in user 7707space. With this capability enabled, all fast orders will be handled completely 7708in the kernel: 7709 7710- SENSE 7711- SENSE RUNNING 7712- EXTERNAL CALL 7713- EMERGENCY SIGNAL 7714- CONDITIONAL EMERGENCY SIGNAL 7715 7716All other orders will be handled completely in user space. 7717 7718Only privileged operation exceptions will be checked for in the kernel (or even 7719in the hardware prior to interception). If this capability is not enabled, the 7720old way of handling SIGP orders is used (partially in kernel and user space). 7721 77227.3 KVM_CAP_S390_VECTOR_REGISTERS 7723--------------------------------- 7724 7725:Architectures: s390 7726:Parameters: none 7727:Returns: 0 on success, negative value on error 7728 7729Allows use of the vector registers introduced with z13 processor, and 7730provides for the synchronization between host and user space. Will 7731return -EINVAL if the machine does not support vectors. 7732 77337.4 KVM_CAP_S390_USER_STSI 7734-------------------------- 7735 7736:Architectures: s390 7737:Parameters: none 7738 7739This capability allows post-handlers for the STSI instruction. After 7740initial handling in the kernel, KVM exits to user space with 7741KVM_EXIT_S390_STSI to allow user space to insert further data. 7742 7743Before exiting to userspace, kvm handlers should fill in s390_stsi field of 7744vcpu->run:: 7745 7746 struct { 7747 __u64 addr; 7748 __u8 ar; 7749 __u8 reserved; 7750 __u8 fc; 7751 __u8 sel1; 7752 __u16 sel2; 7753 } s390_stsi; 7754 7755 @addr - guest address of STSI SYSIB 7756 @fc - function code 7757 @sel1 - selector 1 7758 @sel2 - selector 2 7759 @ar - access register number 7760 7761KVM handlers should exit to userspace with rc = -EREMOTE. 7762 77637.5 KVM_CAP_SPLIT_IRQCHIP 7764------------------------- 7765 7766:Architectures: x86 7767:Parameters: args[0] - number of routes reserved for userspace IOAPICs 7768:Returns: 0 on success, -1 on error 7769 7770Create a local apic for each processor in the kernel. This can be used 7771instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the 7772IOAPIC and PIC (and also the PIT, even though this has to be enabled 7773separately). 7774 7775This capability also enables in kernel routing of interrupt requests; 7776when KVM_CAP_SPLIT_IRQCHIP only routes of KVM_IRQ_ROUTING_MSI type are 7777used in the IRQ routing table. The first args[0] MSI routes are reserved 7778for the IOAPIC pins. Whenever the LAPIC receives an EOI for these routes, 7779a KVM_EXIT_IOAPIC_EOI vmexit will be reported to userspace. 7780 7781Fails if VCPU has already been created, or if the irqchip is already in the 7782kernel (i.e. KVM_CREATE_IRQCHIP has already been called). 7783 77847.6 KVM_CAP_S390_RI 7785------------------- 7786 7787:Architectures: s390 7788:Parameters: none 7789 7790Allows use of runtime-instrumentation introduced with zEC12 processor. 7791Will return -EINVAL if the machine does not support runtime-instrumentation. 7792Will return -EBUSY if a VCPU has already been created. 7793 77947.7 KVM_CAP_X2APIC_API 7795---------------------- 7796 7797:Architectures: x86 7798:Parameters: args[0] - features that should be enabled 7799:Returns: 0 on success, -EINVAL when args[0] contains invalid features 7800 7801Valid feature flags in args[0] are:: 7802 7803 #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) 7804 #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) 7805 7806Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of 7807KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC, 7808allowing the use of 32-bit APIC IDs. See KVM_CAP_X2APIC_API in their 7809respective sections. 7810 7811KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK must be enabled for x2APIC to work 7812in logical mode or with more than 255 VCPUs. Otherwise, KVM treats 0xff 7813as a broadcast even in x2APIC mode in order to support physical x2APIC 7814without interrupt remapping. This is undesirable in logical mode, 7815where 0xff represents CPUs 0-7 in cluster 0. 7816 78177.8 KVM_CAP_S390_USER_INSTR0 7818---------------------------- 7819 7820:Architectures: s390 7821:Parameters: none 7822 7823With this capability enabled, all illegal instructions 0x0000 (2 bytes) will 7824be intercepted and forwarded to user space. User space can use this 7825mechanism e.g. to realize 2-byte software breakpoints. The kernel will 7826not inject an operating exception for these instructions, user space has 7827to take care of that. 7828 7829This capability can be enabled dynamically even if VCPUs were already 7830created and are running. 7831 78327.9 KVM_CAP_S390_GS 7833------------------- 7834 7835:Architectures: s390 7836:Parameters: none 7837:Returns: 0 on success; -EINVAL if the machine does not support 7838 guarded storage; -EBUSY if a VCPU has already been created. 7839 7840Allows use of guarded storage for the KVM guest. 7841 78427.10 KVM_CAP_S390_AIS 7843--------------------- 7844 7845:Architectures: s390 7846:Parameters: none 7847 7848Allow use of adapter-interruption suppression. 7849:Returns: 0 on success; -EBUSY if a VCPU has already been created. 7850 78517.11 KVM_CAP_PPC_SMT 7852-------------------- 7853 7854:Architectures: ppc 7855:Parameters: vsmt_mode, flags 7856 7857Enabling this capability on a VM provides userspace with a way to set 7858the desired virtual SMT mode (i.e. the number of virtual CPUs per 7859virtual core). The virtual SMT mode, vsmt_mode, must be a power of 2 7860between 1 and 8. On POWER8, vsmt_mode must also be no greater than 7861the number of threads per subcore for the host. Currently flags must 7862be 0. A successful call to enable this capability will result in 7863vsmt_mode being returned when the KVM_CAP_PPC_SMT capability is 7864subsequently queried for the VM. This capability is only supported by 7865HV KVM, and can only be set before any VCPUs have been created. 7866The KVM_CAP_PPC_SMT_POSSIBLE capability indicates which virtual SMT 7867modes are available. 7868 78697.12 KVM_CAP_PPC_FWNMI 7870---------------------- 7871 7872:Architectures: ppc 7873:Parameters: none 7874 7875With this capability a machine check exception in the guest address 7876space will cause KVM to exit the guest with NMI exit reason. This 7877enables QEMU to build error log and branch to guest kernel registered 7878machine check handling routine. Without this capability KVM will 7879branch to guests' 0x200 interrupt vector. 7880 78817.13 KVM_CAP_X86_DISABLE_EXITS 7882------------------------------ 7883 7884:Architectures: x86 7885:Parameters: args[0] defines which exits are disabled 7886:Returns: 0 on success, -EINVAL when args[0] contains invalid exits 7887 or if any vCPUs have already been created 7888 7889Valid bits in args[0] are:: 7890 7891 #define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) 7892 #define KVM_X86_DISABLE_EXITS_HLT (1 << 1) 7893 #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) 7894 #define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) 7895 #define KVM_X86_DISABLE_EXITS_APERFMPERF (1 << 4) 7896 7897Enabling this capability on a VM provides userspace with a way to no 7898longer intercept some instructions for improved latency in some 7899workloads, and is suggested when vCPUs are associated to dedicated 7900physical CPUs. More bits can be added in the future; userspace can 7901just pass the KVM_CHECK_EXTENSION result to KVM_ENABLE_CAP to disable 7902all such vmexits. 7903 7904Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits. 7905 7906Virtualizing the ``IA32_APERF`` and ``IA32_MPERF`` MSRs requires more 7907than just disabling APERF/MPERF exits. While both Intel and AMD 7908document strict usage conditions for these MSRs--emphasizing that only 7909the ratio of their deltas over a time interval (T0 to T1) is 7910architecturally defined--simply passing through the MSRs can still 7911produce an incorrect ratio. 7912 7913This erroneous ratio can occur if, between T0 and T1: 7914 79151. The vCPU thread migrates between logical processors. 79162. Live migration or suspend/resume operations take place. 79173. Another task shares the vCPU's logical processor. 79184. C-states lower than C0 are emulated (e.g., via HLT interception). 79195. The guest TSC frequency doesn't match the host TSC frequency. 7920 7921Due to these complexities, KVM does not automatically associate this 7922passthrough capability with the guest CPUID bit, 7923``CPUID.6:ECX.APERFMPERF[bit 0]``. Userspace VMMs that deem this 7924mechanism adequate for virtualizing the ``IA32_APERF`` and 7925``IA32_MPERF`` MSRs must set the guest CPUID bit explicitly. 7926 7927 79287.14 KVM_CAP_S390_HPAGE_1M 7929-------------------------- 7930 7931:Architectures: s390 7932:Parameters: none 7933:Returns: 0 on success, -EINVAL if hpage module parameter was not set 7934 or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL 7935 flag set 7936 7937With this capability the KVM support for memory backing with 1m pages 7938through hugetlbfs can be enabled for a VM. After the capability is 7939enabled, cmma can't be enabled anymore and pfmfi and the storage key 7940interpretation are disabled. If cmma has already been enabled or the 7941hpage module parameter is not set to 1, -EINVAL is returned. 7942 7943While it is generally possible to create a huge page backed VM without 7944this capability, the VM will not be able to run. 7945 79467.15 KVM_CAP_MSR_PLATFORM_INFO 7947------------------------------ 7948 7949:Architectures: x86 7950:Parameters: args[0] whether feature should be enabled or not 7951 7952With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise, 7953a #GP would be raised when the guest tries to access. Currently, this 7954capability does not enable write permissions of this MSR for the guest. 7955 79567.16 KVM_CAP_PPC_NESTED_HV 7957-------------------------- 7958 7959:Architectures: ppc 7960:Parameters: none 7961:Returns: 0 on success, -EINVAL when the implementation doesn't support 7962 nested-HV virtualization. 7963 7964HV-KVM on POWER9 and later systems allows for "nested-HV" 7965virtualization, which provides a way for a guest VM to run guests that 7966can run using the CPU's supervisor mode (privileged non-hypervisor 7967state). Enabling this capability on a VM depends on the CPU having 7968the necessary functionality and on the facility being enabled with a 7969kvm-hv module parameter. 7970 79717.17 KVM_CAP_EXCEPTION_PAYLOAD 7972------------------------------ 7973 7974:Architectures: x86 7975:Parameters: args[0] whether feature should be enabled or not 7976 7977With this capability enabled, CR2 will not be modified prior to the 7978emulated VM-exit when L1 intercepts a #PF exception that occurs in 7979L2. Similarly, for kvm-intel only, DR6 will not be modified prior to 7980the emulated VM-exit when L1 intercepts a #DB exception that occurs in 7981L2. As a result, when KVM_GET_VCPU_EVENTS reports a pending #PF (or 7982#DB) exception for L2, exception.has_payload will be set and the 7983faulting address (or the new DR6 bits*) will be reported in the 7984exception_payload field. Similarly, when userspace injects a #PF (or 7985#DB) into L2 using KVM_SET_VCPU_EVENTS, it is expected to set 7986exception.has_payload and to put the faulting address - or the new DR6 7987bits\ [#]_ - in the exception_payload field. 7988 7989This capability also enables exception.pending in struct 7990kvm_vcpu_events, which allows userspace to distinguish between pending 7991and injected exceptions. 7992 7993 7994.. [#] For the new DR6 bits, note that bit 16 is set iff the #DB exception 7995 will clear DR6.RTM. 7996 79977.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 7998-------------------------------------- 7999 8000:Architectures: x86, arm64, mips 8001:Parameters: args[0] whether feature should be enabled or not 8002 8003Valid flags are:: 8004 8005 #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) 8006 #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) 8007 8008With KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE is set, KVM_GET_DIRTY_LOG will not 8009automatically clear and write-protect all pages that are returned as dirty. 8010Rather, userspace will have to do this operation separately using 8011KVM_CLEAR_DIRTY_LOG. 8012 8013At the cost of a slightly more complicated operation, this provides better 8014scalability and responsiveness for two reasons. First, 8015KVM_CLEAR_DIRTY_LOG ioctl can operate on a 64-page granularity rather 8016than requiring to sync a full memslot; this ensures that KVM does not 8017take spinlocks for an extended period of time. Second, in some cases a 8018large amount of time can pass between a call to KVM_GET_DIRTY_LOG and 8019userspace actually using the data in the page. Pages can be modified 8020during this time, which is inefficient for both the guest and userspace: 8021the guest will incur a higher penalty due to write protection faults, 8022while userspace can see false reports of dirty pages. Manual reprotection 8023helps reducing this time, improving guest performance and reducing the 8024number of dirty log false positives. 8025 8026With KVM_DIRTY_LOG_INITIALLY_SET set, all the bits of the dirty bitmap 8027will be initialized to 1 when created. This also improves performance because 8028dirty logging can be enabled gradually in small chunks on the first call 8029to KVM_CLEAR_DIRTY_LOG. KVM_DIRTY_LOG_INITIALLY_SET depends on 8030KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (it is also only available on 8031x86 and arm64 for now). 8032 8033KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 was previously available under the name 8034KVM_CAP_MANUAL_DIRTY_LOG_PROTECT, but the implementation had bugs that make 8035it hard or impossible to use it correctly. The availability of 8036KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 signals that those bugs are fixed. 8037Userspace should not try to use KVM_CAP_MANUAL_DIRTY_LOG_PROTECT. 8038 80397.19 KVM_CAP_PPC_SECURE_GUEST 8040------------------------------ 8041 8042:Architectures: ppc 8043 8044This capability indicates that KVM is running on a host that has 8045ultravisor firmware and thus can support a secure guest. On such a 8046system, a guest can ask the ultravisor to make it a secure guest, 8047one whose memory is inaccessible to the host except for pages which 8048are explicitly requested to be shared with the host. The ultravisor 8049notifies KVM when a guest requests to become a secure guest, and KVM 8050has the opportunity to veto the transition. 8051 8052If present, this capability can be enabled for a VM, meaning that KVM 8053will allow the transition to secure guest mode. Otherwise KVM will 8054veto the transition. 8055 80567.20 KVM_CAP_HALT_POLL 8057---------------------- 8058 8059:Architectures: all 8060:Target: VM 8061:Parameters: args[0] is the maximum poll time in nanoseconds 8062:Returns: 0 on success; -1 on error 8063 8064KVM_CAP_HALT_POLL overrides the kvm.halt_poll_ns module parameter to set the 8065maximum halt-polling time for all vCPUs in the target VM. This capability can 8066be invoked at any time and any number of times to dynamically change the 8067maximum halt-polling time. 8068 8069See Documentation/virt/kvm/halt-polling.rst for more information on halt 8070polling. 8071 80727.21 KVM_CAP_X86_USER_SPACE_MSR 8073------------------------------- 8074 8075:Architectures: x86 8076:Target: VM 8077:Parameters: args[0] contains the mask of KVM_MSR_EXIT_REASON_* events to report 8078:Returns: 0 on success; -1 on error 8079 8080This capability allows userspace to intercept RDMSR and WRMSR instructions if 8081access to an MSR is denied. By default, KVM injects #GP on denied accesses. 8082 8083When a guest requests to read or write an MSR, KVM may not implement all MSRs 8084that are relevant to a respective system. It also does not differentiate by 8085CPU type. 8086 8087To allow more fine grained control over MSR handling, userspace may enable 8088this capability. With it enabled, MSR accesses that match the mask specified in 8089args[0] and would trigger a #GP inside the guest will instead trigger 8090KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications. Userspace 8091can then implement model specific MSR handling and/or user notifications 8092to inform a user that an MSR was not emulated/virtualized by KVM. 8093 8094The valid mask flags are: 8095 8096============================ =============================================== 8097 KVM_MSR_EXIT_REASON_UNKNOWN intercept accesses to unknown (to KVM) MSRs 8098 KVM_MSR_EXIT_REASON_INVAL intercept accesses that are architecturally 8099 invalid according to the vCPU model and/or mode 8100 KVM_MSR_EXIT_REASON_FILTER intercept accesses that are denied by userspace 8101 via KVM_X86_SET_MSR_FILTER 8102============================ =============================================== 8103 81047.22 KVM_CAP_X86_BUS_LOCK_EXIT 8105------------------------------- 8106 8107:Architectures: x86 8108:Target: VM 8109:Parameters: args[0] defines the policy used when bus locks detected in guest 8110:Returns: 0 on success, -EINVAL when args[0] contains invalid bits 8111 8112Valid bits in args[0] are:: 8113 8114 #define KVM_BUS_LOCK_DETECTION_OFF (1 << 0) 8115 #define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1) 8116 8117Enabling this capability on a VM provides userspace with a way to select a 8118policy to handle the bus locks detected in guest. Userspace can obtain the 8119supported modes from the result of KVM_CHECK_EXTENSION and define it through 8120the KVM_ENABLE_CAP. The supported modes are mutually-exclusive. 8121 8122This capability allows userspace to force VM exits on bus locks detected in the 8123guest, irrespective whether or not the host has enabled split-lock detection 8124(which triggers an #AC exception that KVM intercepts). This capability is 8125intended to mitigate attacks where a malicious/buggy guest can exploit bus 8126locks to degrade the performance of the whole system. 8127 8128If KVM_BUS_LOCK_DETECTION_OFF is set, KVM doesn't force guest bus locks to VM 8129exit, although the host kernel's split-lock #AC detection still applies, if 8130enabled. 8131 8132If KVM_BUS_LOCK_DETECTION_EXIT is set, KVM enables a CPU feature that ensures 8133bus locks in the guest trigger a VM exit, and KVM exits to userspace for all 8134such VM exits, e.g. to allow userspace to throttle the offending guest and/or 8135apply some other policy-based mitigation. When exiting to userspace, KVM sets 8136KVM_RUN_X86_BUS_LOCK in vcpu-run->flags, and conditionally sets the exit_reason 8137to KVM_EXIT_X86_BUS_LOCK. 8138 8139Due to differences in the underlying hardware implementation, the vCPU's RIP at 8140the time of exit diverges between Intel and AMD. On Intel hosts, RIP points at 8141the next instruction, i.e. the exit is trap-like. On AMD hosts, RIP points at 8142the offending instruction, i.e. the exit is fault-like. 8143 8144Note! Detected bus locks may be coincident with other exits to userspace, i.e. 8145KVM_RUN_X86_BUS_LOCK should be checked regardless of the primary exit reason if 8146userspace wants to take action on all detected bus locks. 8147 81487.23 KVM_CAP_PPC_DAWR1 8149---------------------- 8150 8151:Architectures: ppc 8152:Parameters: none 8153:Returns: 0 on success, -EINVAL when CPU doesn't support 2nd DAWR 8154 8155This capability can be used to check / enable 2nd DAWR feature provided 8156by POWER10 processor. 8157 8158 81597.24 KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 8160------------------------------------- 8161 8162:Architectures: x86 SEV enabled 8163:Type: vm 8164:Parameters: args[0] is the fd of the source vm 8165:Returns: 0 on success; ENOTTY on error 8166 8167This capability enables userspace to copy encryption context from the vm 8168indicated by the fd to the vm this is called on. 8169 8170This is intended to support in-guest workloads scheduled by the host. This 8171allows the in-guest workload to maintain its own NPTs and keeps the two vms 8172from accidentally clobbering each other with interrupts and the like (separate 8173APIC/MSRs/etc). 8174 81757.25 KVM_CAP_SGX_ATTRIBUTE 8176-------------------------- 8177 8178:Architectures: x86 8179:Target: VM 8180:Parameters: args[0] is a file handle of a SGX attribute file in securityfs 8181:Returns: 0 on success, -EINVAL if the file handle is invalid or if a requested 8182 attribute is not supported by KVM. 8183 8184KVM_CAP_SGX_ATTRIBUTE enables a userspace VMM to grant a VM access to one or 8185more privileged enclave attributes. args[0] must hold a file handle to a valid 8186SGX attribute file corresponding to an attribute that is supported/restricted 8187by KVM (currently only PROVISIONKEY). 8188 8189The SGX subsystem restricts access to a subset of enclave attributes to provide 8190additional security for an uncompromised kernel, e.g. use of the PROVISIONKEY 8191is restricted to deter malware from using the PROVISIONKEY to obtain a stable 8192system fingerprint. To prevent userspace from circumventing such restrictions 8193by running an enclave in a VM, KVM prevents access to privileged attributes by 8194default. 8195 8196See Documentation/arch/x86/sgx.rst for more details. 8197 81987.27 KVM_CAP_EXIT_ON_EMULATION_FAILURE 8199-------------------------------------- 8200 8201:Architectures: x86 8202:Parameters: args[0] whether the feature should be enabled or not 8203 8204When this capability is enabled, an emulation failure will result in an exit 8205to userspace with KVM_INTERNAL_ERROR (except when the emulator was invoked 8206to handle a VMware backdoor instruction). Furthermore, KVM will now provide up 8207to 15 instruction bytes for any exit to userspace resulting from an emulation 8208failure. When these exits to userspace occur use the emulation_failure struct 8209instead of the internal struct. They both have the same layout, but the 8210emulation_failure struct matches the content better. It also explicitly 8211defines the 'flags' field which is used to describe the fields in the struct 8212that are valid (ie: if KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES is 8213set in the 'flags' field then both 'insn_size' and 'insn_bytes' have valid data 8214in them.) 8215 82167.28 KVM_CAP_ARM_MTE 8217-------------------- 8218 8219:Architectures: arm64 8220:Parameters: none 8221 8222This capability indicates that KVM (and the hardware) supports exposing the 8223Memory Tagging Extensions (MTE) to the guest. It must also be enabled by the 8224VMM before creating any VCPUs to allow the guest access. Note that MTE is only 8225available to a guest running in AArch64 mode and enabling this capability will 8226cause attempts to create AArch32 VCPUs to fail. 8227 8228When enabled the guest is able to access tags associated with any memory given 8229to the guest. KVM will ensure that the tags are maintained during swap or 8230hibernation of the host; however the VMM needs to manually save/restore the 8231tags as appropriate if the VM is migrated. 8232 8233When this capability is enabled all memory in memslots must be mapped as 8234``MAP_ANONYMOUS`` or with a RAM-based file mapping (``tmpfs``, ``memfd``), 8235attempts to create a memslot with an invalid mmap will result in an 8236-EINVAL return. 8237 8238When enabled the VMM may make use of the ``KVM_ARM_MTE_COPY_TAGS`` ioctl to 8239perform a bulk copy of tags to/from the guest. 8240 82417.29 KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 8242------------------------------------- 8243 8244:Architectures: x86 SEV enabled 8245:Type: vm 8246:Parameters: args[0] is the fd of the source vm 8247:Returns: 0 on success 8248 8249This capability enables userspace to migrate the encryption context from the VM 8250indicated by the fd to the VM this is called on. 8251 8252This is intended to support intra-host migration of VMs between userspace VMMs, 8253upgrading the VMM process without interrupting the guest. 8254 82557.31 KVM_CAP_DISABLE_QUIRKS2 8256---------------------------- 8257 8258:Parameters: args[0] - set of KVM quirks to disable 8259:Architectures: x86 8260:Type: vm 8261 8262This capability, if enabled, will cause KVM to disable some behavior 8263quirks. 8264 8265Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of 8266quirks that can be disabled in KVM. 8267 8268The argument to KVM_ENABLE_CAP for this capability is a bitmask of 8269quirks to disable, and must be a subset of the bitmask returned by 8270KVM_CHECK_EXTENSION. 8271 8272The valid bits in cap.args[0] are: 8273 8274=================================== ============================================ 8275 KVM_X86_QUIRK_LINT0_REENABLED By default, the reset value for the LVT 8276 LINT0 register is 0x700 (APIC_MODE_EXTINT). 8277 When this quirk is disabled, the reset value 8278 is 0x10000 (APIC_LVT_MASKED). 8279 8280 KVM_X86_QUIRK_CD_NW_CLEARED By default, KVM clears CR0.CD and CR0.NW on 8281 AMD CPUs to workaround buggy guest firmware 8282 that runs in perpetuity with CR0.CD, i.e. 8283 with caches in "no fill" mode. 8284 8285 When this quirk is disabled, KVM does not 8286 change the value of CR0.CD and CR0.NW. 8287 8288 KVM_X86_QUIRK_LAPIC_MMIO_HOLE By default, the MMIO LAPIC interface is 8289 available even when configured for x2APIC 8290 mode. When this quirk is disabled, KVM 8291 disables the MMIO LAPIC interface if the 8292 LAPIC is in x2APIC mode. 8293 8294 KVM_X86_QUIRK_OUT_7E_INC_RIP By default, KVM pre-increments %rip before 8295 exiting to userspace for an OUT instruction 8296 to port 0x7e. When this quirk is disabled, 8297 KVM does not pre-increment %rip before 8298 exiting to userspace. 8299 8300 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT When this quirk is disabled, KVM sets 8301 CPUID.01H:ECX[bit 3] (MONITOR/MWAIT) if 8302 IA32_MISC_ENABLE[bit 18] (MWAIT) is set. 8303 Additionally, when this quirk is disabled, 8304 KVM clears CPUID.01H:ECX[bit 3] if 8305 IA32_MISC_ENABLE[bit 18] is cleared. 8306 8307 KVM_X86_QUIRK_FIX_HYPERCALL_INSN By default, KVM rewrites guest 8308 VMMCALL/VMCALL instructions to match the 8309 vendor's hypercall instruction for the 8310 system. When this quirk is disabled, KVM 8311 will no longer rewrite invalid guest 8312 hypercall instructions. Executing the 8313 incorrect hypercall instruction will 8314 generate a #UD within the guest. 8315 8316KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if 8317 they are intercepted) as NOPs regardless of 8318 whether or not MONITOR/MWAIT are supported 8319 according to guest CPUID. When this quirk 8320 is disabled and KVM_X86_DISABLE_EXITS_MWAIT 8321 is not set (MONITOR/MWAIT are intercepted), 8322 KVM will inject a #UD on MONITOR/MWAIT if 8323 they're unsupported per guest CPUID. Note, 8324 KVM will modify MONITOR/MWAIT support in 8325 guest CPUID on writes to MISC_ENABLE if 8326 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is 8327 disabled. 8328 8329KVM_X86_QUIRK_SLOT_ZAP_ALL By default, for KVM_X86_DEFAULT_VM VMs, KVM 8330 invalidates all SPTEs in all memslots and 8331 address spaces when a memslot is deleted or 8332 moved. When this quirk is disabled (or the 8333 VM type isn't KVM_X86_DEFAULT_VM), KVM only 8334 ensures the backing memory of the deleted 8335 or moved memslot isn't reachable, i.e KVM 8336 _may_ invalidate only SPTEs related to the 8337 memslot. 8338 8339KVM_X86_QUIRK_STUFF_FEATURE_MSRS By default, at vCPU creation, KVM sets the 8340 vCPU's MSR_IA32_PERF_CAPABILITIES (0x345), 8341 MSR_IA32_ARCH_CAPABILITIES (0x10a), 8342 MSR_PLATFORM_INFO (0xce), and all VMX MSRs 8343 (0x480..0x492) to the maximal capabilities 8344 supported by KVM. KVM also sets 8345 MSR_IA32_UCODE_REV (0x8b) to an arbitrary 8346 value (which is different for Intel vs. 8347 AMD). Lastly, when guest CPUID is set (by 8348 userspace), KVM modifies select VMX MSR 8349 fields to force consistency between guest 8350 CPUID and L2's effective ISA. When this 8351 quirk is disabled, KVM zeroes the vCPU's MSR 8352 values (with two exceptions, see below), 8353 i.e. treats the feature MSRs like CPUID 8354 leaves and gives userspace full control of 8355 the vCPU model definition. This quirk does 8356 not affect VMX MSRs CR0/CR4_FIXED1 (0x487 8357 and 0x489), as KVM does now allow them to 8358 be set by userspace (KVM sets them based on 8359 guest CPUID, for safety purposes). 8360 8361KVM_X86_QUIRK_IGNORE_GUEST_PAT By default, on Intel platforms, KVM ignores 8362 guest PAT and forces the effective memory 8363 type to WB in EPT. The quirk is not available 8364 on Intel platforms which are incapable of 8365 safely honoring guest PAT (i.e., without CPU 8366 self-snoop, KVM always ignores guest PAT and 8367 forces effective memory type to WB). It is 8368 also ignored on AMD platforms or, on Intel, 8369 when a VM has non-coherent DMA devices 8370 assigned; KVM always honors guest PAT in 8371 such case. The quirk is needed to avoid 8372 slowdowns on certain Intel Xeon platforms 8373 (e.g. ICX, SPR) where self-snoop feature is 8374 supported but UC is slow enough to cause 8375 issues with some older guests that use 8376 UC instead of WC to map the video RAM. 8377 Userspace can disable the quirk to honor 8378 guest PAT if it knows that there is no such 8379 guest software, for example if it does not 8380 expose a bochs graphics device (which is 8381 known to have had a buggy driver). 8382=================================== ============================================ 8383 83847.32 KVM_CAP_MAX_VCPU_ID 8385------------------------ 8386 8387:Architectures: x86 8388:Target: VM 8389:Parameters: args[0] - maximum APIC ID value set for current VM 8390:Returns: 0 on success, -EINVAL if args[0] is beyond KVM_MAX_VCPU_IDS 8391 supported in KVM or if it has been set. 8392 8393This capability allows userspace to specify maximum possible APIC ID 8394assigned for current VM session prior to the creation of vCPUs, saving 8395memory for data structures indexed by the APIC ID. Userspace is able 8396to calculate the limit to APIC ID values from designated 8397CPU topology. 8398 8399The value can be changed only until KVM_ENABLE_CAP is set to a nonzero 8400value or until a vCPU is created. Upon creation of the first vCPU, 8401if the value was set to zero or KVM_ENABLE_CAP was not invoked, KVM 8402uses the return value of KVM_CHECK_EXTENSION(KVM_CAP_MAX_VCPU_ID) as 8403the maximum APIC ID. 8404 84057.33 KVM_CAP_X86_NOTIFY_VMEXIT 8406------------------------------ 8407 8408:Architectures: x86 8409:Target: VM 8410:Parameters: args[0] is the value of notify window as well as some flags 8411:Returns: 0 on success, -EINVAL if args[0] contains invalid flags or notify 8412 VM exit is unsupported. 8413 8414Bits 63:32 of args[0] are used for notify window. 8415Bits 31:0 of args[0] are for some flags. Valid bits are:: 8416 8417 #define KVM_X86_NOTIFY_VMEXIT_ENABLED (1 << 0) 8418 #define KVM_X86_NOTIFY_VMEXIT_USER (1 << 1) 8419 8420This capability allows userspace to configure the notify VM exit on/off 8421in per-VM scope during VM creation. Notify VM exit is disabled by default. 8422When userspace sets KVM_X86_NOTIFY_VMEXIT_ENABLED bit in args[0], VMM will 8423enable this feature with the notify window provided, which will generate 8424a VM exit if no event window occurs in VM non-root mode for a specified of 8425time (notify window). 8426 8427If KVM_X86_NOTIFY_VMEXIT_USER is set in args[0], upon notify VM exits happen, 8428KVM would exit to userspace for handling. 8429 8430This capability is aimed to mitigate the threat that malicious VMs can 8431cause CPU stuck (due to event windows don't open up) and make the CPU 8432unavailable to host or other VMs. 8433 84347.35 KVM_CAP_X86_APIC_BUS_CYCLES_NS 8435----------------------------------- 8436 8437:Architectures: x86 8438:Target: VM 8439:Parameters: args[0] is the desired APIC bus clock rate, in nanoseconds 8440:Returns: 0 on success, -EINVAL if args[0] contains an invalid value for the 8441 frequency or if any vCPUs have been created, -ENXIO if a virtual 8442 local APIC has not been created using KVM_CREATE_IRQCHIP. 8443 8444This capability sets the VM's APIC bus clock frequency, used by KVM's in-kernel 8445virtual APIC when emulating APIC timers. KVM's default value can be retrieved 8446by KVM_CHECK_EXTENSION. 8447 8448Note: Userspace is responsible for correctly configuring CPUID 0x15, a.k.a. the 8449core crystal clock frequency, if a non-zero CPUID 0x15 is exposed to the guest. 8450 84517.36 KVM_CAP_DIRTY_LOG_RING/KVM_CAP_DIRTY_LOG_RING_ACQ_REL 8452---------------------------------------------------------- 8453 8454:Architectures: x86, arm64, riscv 8455:Type: vm 8456:Parameters: args[0] - size of the dirty log ring 8457 8458KVM is capable of tracking dirty memory using ring buffers that are 8459mmapped into userspace; there is one dirty ring per vcpu. 8460 8461The dirty ring is available to userspace as an array of 8462``struct kvm_dirty_gfn``. Each dirty entry is defined as:: 8463 8464 struct kvm_dirty_gfn { 8465 __u32 flags; 8466 __u32 slot; /* as_id | slot_id */ 8467 __u64 offset; 8468 }; 8469 8470The following values are defined for the flags field to define the 8471current state of the entry:: 8472 8473 #define KVM_DIRTY_GFN_F_DIRTY BIT(0) 8474 #define KVM_DIRTY_GFN_F_RESET BIT(1) 8475 #define KVM_DIRTY_GFN_F_MASK 0x3 8476 8477Userspace should call KVM_ENABLE_CAP ioctl right after KVM_CREATE_VM 8478ioctl to enable this capability for the new guest and set the size of 8479the rings. Enabling the capability is only allowed before creating any 8480vCPU, and the size of the ring must be a power of two. The larger the 8481ring buffer, the less likely the ring is full and the VM is forced to 8482exit to userspace. The optimal size depends on the workload, but it is 8483recommended that it be at least 64 KiB (4096 entries). 8484 8485Just like for dirty page bitmaps, the buffer tracks writes to 8486all user memory regions for which the KVM_MEM_LOG_DIRTY_PAGES flag was 8487set in KVM_SET_USER_MEMORY_REGION. Once a memory region is registered 8488with the flag set, userspace can start harvesting dirty pages from the 8489ring buffer. 8490 8491An entry in the ring buffer can be unused (flag bits ``00``), 8492dirty (flag bits ``01``) or harvested (flag bits ``1X``). The 8493state machine for the entry is as follows:: 8494 8495 dirtied harvested reset 8496 00 -----------> 01 -------------> 1X -------+ 8497 ^ | 8498 | | 8499 +------------------------------------------+ 8500 8501To harvest the dirty pages, userspace accesses the mmapped ring buffer 8502to read the dirty GFNs. If the flags has the DIRTY bit set (at this stage 8503the RESET bit must be cleared), then it means this GFN is a dirty GFN. 8504The userspace should harvest this GFN and mark the flags from state 8505``01b`` to ``1Xb`` (bit 0 will be ignored by KVM, but bit 1 must be set 8506to show that this GFN is harvested and waiting for a reset), and move 8507on to the next GFN. The userspace should continue to do this until the 8508flags of a GFN have the DIRTY bit cleared, meaning that it has harvested 8509all the dirty GFNs that were available. 8510 8511Note that on weakly ordered architectures, userspace accesses to the 8512ring buffer (and more specifically the 'flags' field) must be ordered, 8513using load-acquire/store-release accessors when available, or any 8514other memory barrier that will ensure this ordering. 8515 8516It's not necessary for userspace to harvest the all dirty GFNs at once. 8517However it must collect the dirty GFNs in sequence, i.e., the userspace 8518program cannot skip one dirty GFN to collect the one next to it. 8519 8520After processing one or more entries in the ring buffer, userspace 8521calls the VM ioctl KVM_RESET_DIRTY_RINGS to notify the kernel about 8522it, so that the kernel will reprotect those collected GFNs. 8523Therefore, the ioctl must be called *before* reading the content of 8524the dirty pages. 8525 8526The dirty ring can get full. When it happens, the KVM_RUN of the 8527vcpu will return with exit reason KVM_EXIT_DIRTY_LOG_FULL. 8528 8529The dirty ring interface has a major difference comparing to the 8530KVM_GET_DIRTY_LOG interface in that, when reading the dirty ring from 8531userspace, it's still possible that the kernel has not yet flushed the 8532processor's dirty page buffers into the kernel buffer (with dirty bitmaps, the 8533flushing is done by the KVM_GET_DIRTY_LOG ioctl). To achieve that, one 8534needs to kick the vcpu out of KVM_RUN using a signal. The resulting 8535vmexit ensures that all dirty GFNs are flushed to the dirty rings. 8536 8537NOTE: KVM_CAP_DIRTY_LOG_RING_ACQ_REL is the only capability that 8538should be exposed by weakly ordered architecture, in order to indicate 8539the additional memory ordering requirements imposed on userspace when 8540reading the state of an entry and mutating it from DIRTY to HARVESTED. 8541Architecture with TSO-like ordering (such as x86) are allowed to 8542expose both KVM_CAP_DIRTY_LOG_RING and KVM_CAP_DIRTY_LOG_RING_ACQ_REL 8543to userspace. 8544 8545After enabling the dirty rings, the userspace needs to detect the 8546capability of KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP to see whether the 8547ring structures can be backed by per-slot bitmaps. With this capability 8548advertised, it means the architecture can dirty guest pages without 8549vcpu/ring context, so that some of the dirty information will still be 8550maintained in the bitmap structure. KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 8551can't be enabled if the capability of KVM_CAP_DIRTY_LOG_RING_ACQ_REL 8552hasn't been enabled, or any memslot has been existing. 8553 8554Note that the bitmap here is only a backup of the ring structure. The 8555use of the ring and bitmap combination is only beneficial if there is 8556only a very small amount of memory that is dirtied out of vcpu/ring 8557context. Otherwise, the stand-alone per-slot bitmap mechanism needs to 8558be considered. 8559 8560To collect dirty bits in the backup bitmap, userspace can use the same 8561KVM_GET_DIRTY_LOG ioctl. KVM_CLEAR_DIRTY_LOG isn't needed as long as all 8562the generation of the dirty bits is done in a single pass. Collecting 8563the dirty bitmap should be the very last thing that the VMM does before 8564considering the state as complete. VMM needs to ensure that the dirty 8565state is final and avoid missing dirty pages from another ioctl ordered 8566after the bitmap collection. 8567 8568NOTE: Multiple examples of using the backup bitmap: (1) save vgic/its 8569tables through command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} on 8570KVM device "kvm-arm-vgic-its". (2) restore vgic/its tables through 8571command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_RESTORE_TABLES} on KVM device 8572"kvm-arm-vgic-its". VGICv3 LPI pending status is restored. (3) save 8573vgic3 pending table through KVM_DEV_ARM_VGIC_{GRP_CTRL, SAVE_PENDING_TABLES} 8574command on KVM device "kvm-arm-vgic-v3". 8575 85767.37 KVM_CAP_PMU_CAPABILITY 8577--------------------------- 8578 8579:Architectures: x86 8580:Type: vm 8581:Parameters: arg[0] is bitmask of PMU virtualization capabilities. 8582:Returns: 0 on success, -EINVAL when arg[0] contains invalid bits 8583 8584This capability alters PMU virtualization in KVM. 8585 8586Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of 8587PMU virtualization capabilities that can be adjusted on a VM. 8588 8589The argument to KVM_ENABLE_CAP is also a bitmask and selects specific 8590PMU virtualization capabilities to be applied to the VM. This can 8591only be invoked on a VM prior to the creation of VCPUs. 8592 8593At this time, KVM_PMU_CAP_DISABLE is the only capability. Setting 8594this capability will disable PMU virtualization for that VM. Usermode 8595should adjust CPUID leaf 0xA to reflect that the PMU is disabled. 8596 85977.38 KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 8598------------------------------------- 8599 8600:Architectures: x86 8601:Type: vm 8602:Parameters: arg[0] must be 0. 8603:Returns: 0 on success, -EPERM if the userspace process does not 8604 have CAP_SYS_BOOT, -EINVAL if args[0] is not 0 or any vCPUs have been 8605 created. 8606 8607This capability disables the NX huge pages mitigation for iTLB MULTIHIT. 8608 8609The capability has no effect if the nx_huge_pages module parameter is not set. 8610 8611This capability may only be set before any vCPUs are created. 8612 86137.39 KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 8614--------------------------------------- 8615 8616:Architectures: arm64 8617:Type: vm 8618:Parameters: arg[0] is the new split chunk size. 8619:Returns: 0 on success, -EINVAL if any memslot was already created. 8620 8621This capability sets the chunk size used in Eager Page Splitting. 8622 8623Eager Page Splitting improves the performance of dirty-logging (used 8624in live migrations) when guest memory is backed by huge-pages. It 8625avoids splitting huge-pages (into PAGE_SIZE pages) on fault, by doing 8626it eagerly when enabling dirty logging (with the 8627KVM_MEM_LOG_DIRTY_PAGES flag for a memory region), or when using 8628KVM_CLEAR_DIRTY_LOG. 8629 8630The chunk size specifies how many pages to break at a time, using a 8631single allocation for each chunk. Bigger the chunk size, more pages 8632need to be allocated ahead of time. 8633 8634The chunk size needs to be a valid block size. The list of acceptable 8635block sizes is exposed in KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES as a 863664-bit bitmap (each bit describing a block size). The default value is 86370, to disable the eager page splitting. 8638 86397.40 KVM_CAP_EXIT_HYPERCALL 8640--------------------------- 8641 8642:Architectures: x86 8643:Type: vm 8644 8645This capability, if enabled, will cause KVM to exit to userspace 8646with KVM_EXIT_HYPERCALL exit reason to process some hypercalls. 8647 8648Calling KVM_CHECK_EXTENSION for this capability will return a bitmask 8649of hypercalls that can be configured to exit to userspace. 8650Right now, the only such hypercall is KVM_HC_MAP_GPA_RANGE. 8651 8652The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset 8653of the result of KVM_CHECK_EXTENSION. KVM will forward to userspace 8654the hypercalls whose corresponding bit is in the argument, and return 8655ENOSYS for the others. 8656 86577.41 KVM_CAP_ARM_SYSTEM_SUSPEND 8658------------------------------- 8659 8660:Architectures: arm64 8661:Type: vm 8662 8663When enabled, KVM will exit to userspace with KVM_EXIT_SYSTEM_EVENT of 8664type KVM_SYSTEM_EVENT_SUSPEND to process the guest suspend request. 8665 86667.42 KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 8667------------------------------------- 8668 8669:Architectures: arm64 8670:Target: VM 8671:Parameters: None 8672:Returns: 0 on success, -EINVAL if vCPUs have been created before enabling this 8673 capability. 8674 8675This capability changes the behavior of the registers that identify a PE 8676implementation of the Arm architecture: MIDR_EL1, REVIDR_EL1, and AIDR_EL1. 8677By default, these registers are visible to userspace but treated as invariant. 8678 8679When this capability is enabled, KVM allows userspace to change the 8680aforementioned registers before the first KVM_RUN. These registers are VM 8681scoped, meaning that the same set of values are presented on all vCPUs in a 8682given VM. 8683 86847.43 KVM_CAP_RISCV_MP_STATE_RESET 8685--------------------------------- 8686 8687:Architectures: riscv 8688:Type: VM 8689:Parameters: None 8690:Returns: 0 on success, -EINVAL if arg[0] is not zero 8691 8692When this capability is enabled, KVM resets the VCPU when setting 8693MP_STATE_INIT_RECEIVED through IOCTL. The original MP_STATE is preserved. 8694 86957.43 KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 8696------------------------------------------- 8697 8698:Architectures: arm64 8699:Target: VM 8700:Parameters: None 8701 8702This capability indicate to the userspace whether a PFNMAP memory region 8703can be safely mapped as cacheable. This relies on the presence of 8704force write back (FWB) feature support on the hardware. 8705 87068. Other capabilities. 8707====================== 8708 8709This section lists capabilities that give information about other 8710features of the KVM implementation. 8711 87128.1 KVM_CAP_PPC_HWRNG 8713--------------------- 8714 8715:Architectures: ppc 8716 8717This capability, if KVM_CHECK_EXTENSION indicates that it is 8718available, means that the kernel has an implementation of the 8719H_RANDOM hypercall backed by a hardware random-number generator. 8720If present, the kernel H_RANDOM handler can be enabled for guest use 8721with the KVM_CAP_PPC_ENABLE_HCALL capability. 8722 87238.3 KVM_CAP_PPC_MMU_RADIX 8724------------------------- 8725 8726:Architectures: ppc 8727 8728This capability, if KVM_CHECK_EXTENSION indicates that it is 8729available, means that the kernel can support guests using the 8730radix MMU defined in Power ISA V3.00 (as implemented in the POWER9 8731processor). 8732 87338.4 KVM_CAP_PPC_MMU_HASH_V3 8734--------------------------- 8735 8736:Architectures: ppc 8737 8738This capability, if KVM_CHECK_EXTENSION indicates that it is 8739available, means that the kernel can support guests using the 8740hashed page table MMU defined in Power ISA V3.00 (as implemented in 8741the POWER9 processor), including in-memory segment tables. 8742 87438.5 KVM_CAP_MIPS_VZ 8744------------------- 8745 8746:Architectures: mips 8747 8748This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that 8749it is available, means that full hardware assisted virtualization capabilities 8750of the hardware are available for use through KVM. An appropriate 8751KVM_VM_MIPS_* type must be passed to KVM_CREATE_VM to create a VM which 8752utilises it. 8753 8754If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is 8755available, it means that the VM is using full hardware assisted virtualization 8756capabilities of the hardware. This is useful to check after creating a VM with 8757KVM_VM_MIPS_DEFAULT. 8758 8759The value returned by KVM_CHECK_EXTENSION should be compared against known 8760values (see below). All other values are reserved. This is to allow for the 8761possibility of other hardware assisted virtualization implementations which 8762may be incompatible with the MIPS VZ ASE. 8763 8764== ========================================================================== 8765 0 The trap & emulate implementation is in use to run guest code in user 8766 mode. Guest virtual memory segments are rearranged to fit the guest in the 8767 user mode address space. 8768 8769 1 The MIPS VZ ASE is in use, providing full hardware assisted 8770 virtualization, including standard guest virtual memory segments. 8771== ========================================================================== 8772 87738.7 KVM_CAP_MIPS_64BIT 8774---------------------- 8775 8776:Architectures: mips 8777 8778This capability indicates the supported architecture type of the guest, i.e. the 8779supported register and address width. 8780 8781The values returned when this capability is checked by KVM_CHECK_EXTENSION on a 8782kvm VM handle correspond roughly to the CP0_Config.AT register field, and should 8783be checked specifically against known values (see below). All other values are 8784reserved. 8785 8786== ======================================================================== 8787 0 MIPS32 or microMIPS32. 8788 Both registers and addresses are 32-bits wide. 8789 It will only be possible to run 32-bit guest code. 8790 8791 1 MIPS64 or microMIPS64 with access only to 32-bit compatibility segments. 8792 Registers are 64-bits wide, but addresses are 32-bits wide. 8793 64-bit guest code may run but cannot access MIPS64 memory segments. 8794 It will also be possible to run 32-bit guest code. 8795 8796 2 MIPS64 or microMIPS64 with access to all address segments. 8797 Both registers and addresses are 64-bits wide. 8798 It will be possible to run 64-bit or 32-bit guest code. 8799== ======================================================================== 8800 88018.9 KVM_CAP_ARM_USER_IRQ 8802------------------------ 8803 8804:Architectures: arm64 8805 8806This capability, if KVM_CHECK_EXTENSION indicates that it is available, means 8807that if userspace creates a VM without an in-kernel interrupt controller, it 8808will be notified of changes to the output level of in-kernel emulated devices, 8809which can generate virtual interrupts, presented to the VM. 8810For such VMs, on every return to userspace, the kernel 8811updates the vcpu's run->s.regs.device_irq_level field to represent the actual 8812output level of the device. 8813 8814Whenever kvm detects a change in the device output level, kvm guarantees at 8815least one return to userspace before running the VM. This exit could either 8816be a KVM_EXIT_INTR or any other exit event, like KVM_EXIT_MMIO. This way, 8817userspace can always sample the device output level and re-compute the state of 8818the userspace interrupt controller. Userspace should always check the state 8819of run->s.regs.device_irq_level on every kvm exit. 8820The value in run->s.regs.device_irq_level can represent both level and edge 8821triggered interrupt signals, depending on the device. Edge triggered interrupt 8822signals will exit to userspace with the bit in run->s.regs.device_irq_level 8823set exactly once per edge signal. 8824 8825The field run->s.regs.device_irq_level is available independent of 8826run->kvm_valid_regs or run->kvm_dirty_regs bits. 8827 8828If KVM_CAP_ARM_USER_IRQ is supported, the KVM_CHECK_EXTENSION ioctl returns a 8829number larger than 0 indicating the version of this capability is implemented 8830and thereby which bits in run->s.regs.device_irq_level can signal values. 8831 8832Currently the following bits are defined for the device_irq_level bitmap:: 8833 8834 KVM_CAP_ARM_USER_IRQ >= 1: 8835 8836 KVM_ARM_DEV_EL1_VTIMER - EL1 virtual timer 8837 KVM_ARM_DEV_EL1_PTIMER - EL1 physical timer 8838 KVM_ARM_DEV_PMU - ARM PMU overflow interrupt signal 8839 8840Future versions of kvm may implement additional events. These will get 8841indicated by returning a higher number from KVM_CHECK_EXTENSION and will be 8842listed above. 8843 88448.10 KVM_CAP_PPC_SMT_POSSIBLE 8845----------------------------- 8846 8847:Architectures: ppc 8848 8849Querying this capability returns a bitmap indicating the possible 8850virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N 8851(counting from the right) is set, then a virtual SMT mode of 2^N is 8852available. 8853 88548.12 KVM_CAP_HYPERV_VP_INDEX 8855---------------------------- 8856 8857:Architectures: x86 8858 8859This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its 8860value is used to denote the target vcpu for a SynIC interrupt. For 8861compatibility, KVM initializes this msr to KVM's internal vcpu index. When this 8862capability is absent, userspace can still query this msr's value. 8863 88648.13 KVM_CAP_S390_AIS_MIGRATION 8865------------------------------- 8866 8867:Architectures: s390 8868 8869This capability indicates if the flic device will be able to get/set the 8870AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows 8871to discover this without having to create a flic device. 8872 88738.14 KVM_CAP_S390_PSW 8874--------------------- 8875 8876:Architectures: s390 8877 8878This capability indicates that the PSW is exposed via the kvm_run structure. 8879 88808.15 KVM_CAP_S390_GMAP 8881---------------------- 8882 8883:Architectures: s390 8884 8885This capability indicates that the user space memory used as guest mapping can 8886be anywhere in the user memory address space, as long as the memory slots are 8887aligned and sized to a segment (1MB) boundary. 8888 88898.16 KVM_CAP_S390_COW 8890--------------------- 8891 8892:Architectures: s390 8893 8894This capability indicates that the user space memory used as guest mapping can 8895use copy-on-write semantics as well as dirty pages tracking via read-only page 8896tables. 8897 88988.17 KVM_CAP_S390_BPB 8899--------------------- 8900 8901:Architectures: s390 8902 8903This capability indicates that kvm will implement the interfaces to handle 8904reset, migration and nested KVM for branch prediction blocking. The stfle 8905facility 82 should not be provided to the guest without this capability. 8906 89078.18 KVM_CAP_HYPERV_TLBFLUSH 8908---------------------------- 8909 8910:Architectures: x86 8911 8912This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush 8913hypercalls: 8914HvFlushVirtualAddressSpace, HvFlushVirtualAddressSpaceEx, 8915HvFlushVirtualAddressList, HvFlushVirtualAddressListEx. 8916 89178.19 KVM_CAP_ARM_INJECT_SERROR_ESR 8918---------------------------------- 8919 8920:Architectures: arm64 8921 8922This capability indicates that userspace can specify (via the 8923KVM_SET_VCPU_EVENTS ioctl) the syndrome value reported to the guest when it 8924takes a virtual SError interrupt exception. 8925If KVM advertises this capability, userspace can only specify the ISS field for 8926the ESR syndrome. Other parts of the ESR, such as the EC are generated by the 8927CPU when the exception is taken. If this virtual SError is taken to EL1 using 8928AArch64, this value will be reported in the ISS field of ESR_ELx. 8929 8930See KVM_CAP_VCPU_EVENTS for more details. 8931 89328.20 KVM_CAP_HYPERV_SEND_IPI 8933---------------------------- 8934 8935:Architectures: x86 8936 8937This capability indicates that KVM supports paravirtualized Hyper-V IPI send 8938hypercalls: 8939HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx. 8940 89418.22 KVM_CAP_S390_VCPU_RESETS 8942----------------------------- 8943 8944:Architectures: s390 8945 8946This capability indicates that the KVM_S390_NORMAL_RESET and 8947KVM_S390_CLEAR_RESET ioctls are available. 8948 89498.23 KVM_CAP_S390_PROTECTED 8950--------------------------- 8951 8952:Architectures: s390 8953 8954This capability indicates that the Ultravisor has been initialized and 8955KVM can therefore start protected VMs. 8956This capability governs the KVM_S390_PV_COMMAND ioctl and the 8957KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected 8958guests when the state change is invalid. 8959 89608.24 KVM_CAP_STEAL_TIME 8961----------------------- 8962 8963:Architectures: arm64, x86 8964 8965This capability indicates that KVM supports steal time accounting. 8966When steal time accounting is supported it may be enabled with 8967architecture-specific interfaces. This capability and the architecture- 8968specific interfaces must be consistent, i.e. if one says the feature 8969is supported, than the other should as well and vice versa. For arm64 8970see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL". 8971For x86 see Documentation/virt/kvm/x86/msr.rst "MSR_KVM_STEAL_TIME". 8972 89738.25 KVM_CAP_S390_DIAG318 8974------------------------- 8975 8976:Architectures: s390 8977 8978This capability enables a guest to set information about its control program 8979(i.e. guest kernel type and version). The information is helpful during 8980system/firmware service events, providing additional data about the guest 8981environments running on the machine. 8982 8983The information is associated with the DIAGNOSE 0x318 instruction, which sets 8984an 8-byte value consisting of a one-byte Control Program Name Code (CPNC) and 8985a 7-byte Control Program Version Code (CPVC). The CPNC determines what 8986environment the control program is running in (e.g. Linux, z/VM...), and the 8987CPVC is used for information specific to OS (e.g. Linux version, Linux 8988distribution...) 8989 8990If this capability is available, then the CPNC and CPVC can be synchronized 8991between KVM and userspace via the sync regs mechanism (KVM_SYNC_DIAG318). 8992 89938.26 KVM_CAP_X86_USER_SPACE_MSR 8994------------------------------- 8995 8996:Architectures: x86 8997 8998This capability indicates that KVM supports deflection of MSR reads and 8999writes to user space. It can be enabled on a VM level. If enabled, MSR 9000accesses that would usually trigger a #GP by KVM into the guest will 9001instead get bounced to user space through the KVM_EXIT_X86_RDMSR and 9002KVM_EXIT_X86_WRMSR exit notifications. 9003 90048.27 KVM_CAP_X86_MSR_FILTER 9005--------------------------- 9006 9007:Architectures: x86 9008 9009This capability indicates that KVM supports that accesses to user defined MSRs 9010may be rejected. With this capability exposed, KVM exports new VM ioctl 9011KVM_X86_SET_MSR_FILTER which user space can call to specify bitmaps of MSR 9012ranges that KVM should deny access to. 9013 9014In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to 9015trap and emulate MSRs that are outside of the scope of KVM as well as 9016limit the attack surface on KVM's MSR emulation code. 9017 90188.30 KVM_CAP_XEN_HVM 9019-------------------- 9020 9021:Architectures: x86 9022 9023This capability indicates the features that Xen supports for hosting Xen 9024PVHVM guests. Valid flags are:: 9025 9026 #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) 9027 #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) 9028 #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) 9029 #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) 9030 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) 9031 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) 9032 #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) 9033 #define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) 9034 9035The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG 9036ioctl is available, for the guest to set its hypercall page. 9037 9038If KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL is also set, the same flag may also be 9039provided in the flags to KVM_XEN_HVM_CONFIG, without providing hypercall page 9040contents, to request that KVM generate hypercall page content automatically 9041and also enable interception of guest hypercalls with KVM_EXIT_XEN. 9042 9043The KVM_XEN_HVM_CONFIG_SHARED_INFO flag indicates the availability of the 9044KVM_XEN_HVM_SET_ATTR, KVM_XEN_HVM_GET_ATTR, KVM_XEN_VCPU_SET_ATTR and 9045KVM_XEN_VCPU_GET_ATTR ioctls, as well as the delivery of exception vectors 9046for event channel upcalls when the evtchn_upcall_pending field of a vcpu's 9047vcpu_info is set. 9048 9049The KVM_XEN_HVM_CONFIG_RUNSTATE flag indicates that the runstate-related 9050features KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR/_CURRENT/_DATA/_ADJUST are 9051supported by the KVM_XEN_VCPU_SET_ATTR/KVM_XEN_VCPU_GET_ATTR ioctls. 9052 9053The KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL flag indicates that IRQ routing entries 9054of the type KVM_IRQ_ROUTING_XEN_EVTCHN are supported, with the priority 9055field set to indicate 2 level event channel delivery. 9056 9057The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indicates that KVM supports 9058injecting event channel events directly into the guest with the 9059KVM_XEN_HVM_EVTCHN_SEND ioctl. It also indicates support for the 9060KVM_XEN_ATTR_TYPE_EVTCHN/XEN_VERSION HVM attributes and the 9061KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID/TIMER/UPCALL_VECTOR vCPU attributes. 9062related to event channel delivery, timers, and the XENVER_version 9063interception. 9064 9065The KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG flag indicates that KVM supports 9066the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute in the KVM_XEN_SET_ATTR 9067and KVM_XEN_GET_ATTR ioctls. This controls whether KVM will set the 9068XEN_RUNSTATE_UPDATE flag in guest memory mapped vcpu_runstate_info during 9069updates of the runstate information. Note that versions of KVM which support 9070the RUNSTATE feature above, but not the RUNSTATE_UPDATE_FLAG feature, will 9071always set the XEN_RUNSTATE_UPDATE flag when updating the guest structure, 9072which is perhaps counterintuitive. When this flag is advertised, KVM will 9073behave more correctly, not using the XEN_RUNSTATE_UPDATE flag until/unless 9074specifically enabled (by the guest making the hypercall, causing the VMM 9075to enable the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute). 9076 9077The KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag indicates that KVM supports 9078clearing the PVCLOCK_TSC_STABLE_BIT flag in Xen pvclock sources. This will be 9079done when the KVM_CAP_XEN_HVM ioctl sets the 9080KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag. 9081 90828.31 KVM_CAP_SPAPR_MULTITCE 9083--------------------------- 9084 9085:Architectures: ppc 9086:Type: vm 9087 9088This capability means the kernel is capable of handling hypercalls 9089H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user 9090space. This significantly accelerates DMA operations for PPC KVM guests. 9091User space should expect that its handlers for these hypercalls 9092are not going to be called if user space previously registered LIOBN 9093in KVM (via KVM_CREATE_SPAPR_TCE or similar calls). 9094 9095In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest, 9096user space might have to advertise it for the guest. For example, 9097IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is 9098present in the "ibm,hypertas-functions" device-tree property. 9099 9100The hypercalls mentioned above may or may not be processed successfully 9101in the kernel based fast path. If they can not be handled by the kernel, 9102they will get passed on to user space. So user space still has to have 9103an implementation for these despite the in kernel acceleration. 9104 9105This capability is always enabled. 9106 91078.32 KVM_CAP_PTP_KVM 9108-------------------- 9109 9110:Architectures: arm64 9111 9112This capability indicates that the KVM virtual PTP service is 9113supported in the host. A VMM can check whether the service is 9114available to the guest on migration. 9115 91168.37 KVM_CAP_S390_PROTECTED_DUMP 9117-------------------------------- 9118 9119:Architectures: s390 9120:Type: vm 9121 9122This capability indicates that KVM and the Ultravisor support dumping 9123PV guests. The `KVM_PV_DUMP` command is available for the 9124`KVM_S390_PV_COMMAND` ioctl and the `KVM_PV_INFO` command provides 9125dump related UV data. Also the vcpu ioctl `KVM_S390_PV_CPU_COMMAND` is 9126available and supports the `KVM_PV_DUMP_CPU` subcommand. 9127 91288.39 KVM_CAP_S390_CPU_TOPOLOGY 9129------------------------------ 9130 9131:Architectures: s390 9132:Type: vm 9133 9134This capability indicates that KVM will provide the S390 CPU Topology 9135facility which consist of the interpretation of the PTF instruction for 9136the function code 2 along with interception and forwarding of both the 9137PTF instruction with function codes 0 or 1 and the STSI(15,1,x) 9138instruction to the userland hypervisor. 9139 9140The stfle facility 11, CPU Topology facility, should not be indicated 9141to the guest without this capability. 9142 9143When this capability is present, KVM provides a new attribute group 9144on vm fd, KVM_S390_VM_CPU_TOPOLOGY. 9145This new attribute allows to get, set or clear the Modified Change 9146Topology Report (MTCR) bit of the SCA through the kvm_device_attr 9147structure. 9148 9149When getting the Modified Change Topology Report value, the attr->addr 9150must point to a byte where the value will be stored or retrieved from. 9151 91528.41 KVM_CAP_VM_TYPES 9153--------------------- 9154 9155:Architectures: x86 9156:Type: system ioctl 9157 9158This capability returns a bitmap of support VM types. The 1-setting of bit @n 9159means the VM type with value @n is supported. Possible values of @n are:: 9160 9161 #define KVM_X86_DEFAULT_VM 0 9162 #define KVM_X86_SW_PROTECTED_VM 1 9163 #define KVM_X86_SEV_VM 2 9164 #define KVM_X86_SEV_ES_VM 3 9165 9166Note, KVM_X86_SW_PROTECTED_VM is currently only for development and testing. 9167Do not use KVM_X86_SW_PROTECTED_VM for "real" VMs, and especially not in 9168production. The behavior and effective ABI for software-protected VMs is 9169unstable. 9170 91718.42 KVM_CAP_PPC_RPT_INVALIDATE 9172------------------------------- 9173 9174:Architectures: ppc 9175 9176This capability indicates that the kernel is capable of handling 9177H_RPT_INVALIDATE hcall. 9178 9179In order to enable the use of H_RPT_INVALIDATE in the guest, 9180user space might have to advertise it for the guest. For example, 9181IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is 9182present in the "ibm,hypertas-functions" device-tree property. 9183 9184This capability is enabled for hypervisors on platforms like POWER9 9185that support radix MMU. 9186 91878.43 KVM_CAP_PPC_AIL_MODE_3 9188--------------------------- 9189 9190:Architectures: ppc 9191 9192This capability indicates that the kernel supports the mode 3 setting for the 9193"Address Translation Mode on Interrupt" aka "Alternate Interrupt Location" 9194resource that is controlled with the H_SET_MODE hypercall. 9195 9196This capability allows a guest kernel to use a better-performance mode for 9197handling interrupts and system calls. 9198 91998.44 KVM_CAP_MEMORY_FAULT_INFO 9200------------------------------ 9201 9202:Architectures: x86 9203 9204The presence of this capability indicates that KVM_RUN will fill 9205kvm_run.memory_fault if KVM cannot resolve a guest page fault VM-Exit, e.g. if 9206there is a valid memslot but no backing VMA for the corresponding host virtual 9207address. 9208 9209The information in kvm_run.memory_fault is valid if and only if KVM_RUN returns 9210an error with errno=EFAULT or errno=EHWPOISON *and* kvm_run.exit_reason is set 9211to KVM_EXIT_MEMORY_FAULT. 9212 9213Note: Userspaces which attempt to resolve memory faults so that they can retry 9214KVM_RUN are encouraged to guard against repeatedly receiving the same 9215error/annotated fault. 9216 9217See KVM_EXIT_MEMORY_FAULT for more information. 9218 92198.45 KVM_CAP_X86_GUEST_MODE 9220--------------------------- 9221 9222:Architectures: x86 9223 9224The presence of this capability indicates that KVM_RUN will update the 9225KVM_RUN_X86_GUEST_MODE bit in kvm_run.flags to indicate whether the 9226vCPU was executing nested guest code when it exited. 9227 9228KVM exits with the register state of either the L1 or L2 guest 9229depending on which executed at the time of an exit. Userspace must 9230take care to differentiate between these cases. 9231 92329. Known KVM API problems 9233========================= 9234 9235In some cases, KVM's API has some inconsistencies or common pitfalls 9236that userspace need to be aware of. This section details some of 9237these issues. 9238 9239Most of them are architecture specific, so the section is split by 9240architecture. 9241 92429.1. x86 9243-------- 9244 9245``KVM_GET_SUPPORTED_CPUID`` issues 9246^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 9247 9248In general, ``KVM_GET_SUPPORTED_CPUID`` is designed so that it is possible 9249to take its result and pass it directly to ``KVM_SET_CPUID2``. This section 9250documents some cases in which that requires some care. 9251 9252Local APIC features 9253~~~~~~~~~~~~~~~~~~~ 9254 9255CPU[EAX=1]:ECX[21] (X2APIC) is reported by ``KVM_GET_SUPPORTED_CPUID``, 9256but it can only be enabled if ``KVM_CREATE_IRQCHIP`` or 9257``KVM_ENABLE_CAP(KVM_CAP_IRQCHIP_SPLIT)`` are used to enable in-kernel emulation of 9258the local APIC. 9259 9260The same is true for the ``KVM_FEATURE_PV_UNHALT`` paravirtualized feature. 9261 9262On older versions of Linux, CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by 9263``KVM_GET_SUPPORTED_CPUID``, but it can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` 9264is present and the kernel has enabled in-kernel emulation of the local APIC. 9265On newer versions, ``KVM_GET_SUPPORTED_CPUID`` does report the bit as available. 9266 9267CPU topology 9268~~~~~~~~~~~~ 9269 9270Several CPUID values include topology information for the host CPU: 92710x0b and 0x1f for Intel systems, 0x8000001e for AMD systems. Different 9272versions of KVM return different values for this information and userspace 9273should not rely on it. Currently they return all zeroes. 9274 9275If userspace wishes to set up a guest topology, it should be careful that 9276the values of these three leaves differ for each CPU. In particular, 9277the APIC ID is found in EDX for all subleaves of 0x0b and 0x1f, and in EAX 9278for 0x8000001e; the latter also encodes the core id and node id in bits 92797:0 of EBX and ECX respectively. 9280 9281Obsolete ioctls and capabilities 9282^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 9283 9284KVM_CAP_DISABLE_QUIRKS does not let userspace know which quirks are actually 9285available. Use ``KVM_CHECK_EXTENSION(KVM_CAP_DISABLE_QUIRKS2)`` instead if 9286available. 9287 9288Ordering of KVM_GET_*/KVM_SET_* ioctls 9289^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 9290 9291TBD 9292