1
0
Fork 0
mirror of synced 2025-03-06 20:59:54 +01:00
linux/arch/x86/include/asm/hyperv-tlfs.h
Linus Torvalds 49d5759268 ARM:
- Provide a virtual cache topology to the guest to avoid
   inconsistencies with migration on heterogenous systems. Non secure
   software has no practical need to traverse the caches by set/way in
   the first place.
 
 - Add support for taking stage-2 access faults in parallel. This was an
   accidental omission in the original parallel faults implementation,
   but should provide a marginal improvement to machines w/o FEAT_HAFDBS
   (such as hardware from the fruit company).
 
 - A preamble to adding support for nested virtualization to KVM,
   including vEL2 register state, rudimentary nested exception handling
   and masking unsupported features for nested guests.
 
 - Fixes to the PSCI relay that avoid an unexpected host SVE trap when
   resuming a CPU when running pKVM.
 
 - VGIC maintenance interrupt support for the AIC
 
 - Improvements to the arch timer emulation, primarily aimed at reducing
   the trap overhead of running nested.
 
 - Add CONFIG_USERFAULTFD to the KVM selftests config fragment in the
   interest of CI systems.
 
 - Avoid VM-wide stop-the-world operations when a vCPU accesses its own
   redistributor.
 
 - Serialize when toggling CPACR_EL1.SMEN to avoid unexpected exceptions
   in the host.
 
 - Aesthetic and comment/kerneldoc fixes
 
 - Drop the vestiges of the old Columbia mailing list and add [Oliver]
   as co-maintainer
 
 This also drags in arm64's 'for-next/sme2' branch, because both it and
 the PSCI relay changes touch the EL2 initialization code.
 
 RISC-V:
 
 - Fix wrong usage of PGDIR_SIZE instead of PUD_SIZE
 
 - Correctly place the guest in S-mode after redirecting a trap to the guest
 
 - Redirect illegal instruction traps to guest
 
 - SBI PMU support for guest
 
 s390:
 
 - Two patches sorting out confusion between virtual and physical
   addresses, which currently are the same on s390.
 
 - A new ioctl that performs cmpxchg on guest memory
 
 - A few fixes
 
 x86:
 
 - Change tdp_mmu to a read-only parameter
 
 - Separate TDP and shadow MMU page fault paths
 
 - Enable Hyper-V invariant TSC control
 
 - Fix a variety of APICv and AVIC bugs, some of them real-world,
   some of them affecting architecurally legal but unlikely to
   happen in practice
 
 - Mark APIC timer as expired if its in one-shot mode and the count
   underflows while the vCPU task was being migrated
 
 - Advertise support for Intel's new fast REP string features
 
 - Fix a double-shootdown issue in the emergency reboot code
 
 - Ensure GIF=1 and disable SVM during an emergency reboot, i.e. give SVM
   similar treatment to VMX
 
 - Update Xen's TSC info CPUID sub-leaves as appropriate
 
 - Add support for Hyper-V's extended hypercalls, where "support" at this
   point is just forwarding the hypercalls to userspace
 
 - Clean up the kvm->lock vs. kvm->srcu sequences when updating the PMU and
   MSR filters
 
 - One-off fixes and cleanups
 
 - Fix and cleanup the range-based TLB flushing code, used when KVM is
   running on Hyper-V
 
 - Add support for filtering PMU events using a mask.  If userspace
   wants to restrict heavily what events the guest can use, it can now
   do so without needing an absurd number of filter entries
 
 - Clean up KVM's handling of "PMU MSRs to save", especially when vPMU
   support is disabled
 
 - Add PEBS support for Intel Sapphire Rapids
 
 - Fix a mostly benign overflow bug in SEV's send|receive_update_data()
 
 - Move several SVM-specific flags into vcpu_svm
 
 x86 Intel:
 
 - Handle NMI VM-Exits before leaving the noinstr region
 
 - A few trivial cleanups in the VM-Enter flows
 
 - Stop enabling VMFUNC for L1 purely to document that KVM doesn't support
   EPTP switching (or any other VM function) for L1
 
 - Fix a crash when using eVMCS's enlighted MSR bitmaps
 
 Generic:
 
 - Clean up the hardware enable and initialization flow, which was
   scattered around multiple arch-specific hooks.  Instead, just
   let the arch code call into generic code.  Both x86 and ARM should
   benefit from not having to fight common KVM code's notion of how
   to do initialization.
 
 - Account allocations in generic kvm_arch_alloc_vm()
 
 - Fix a memory leak if coalesced MMIO unregistration fails
 
 selftests:
 
 - On x86, cache the CPU vendor (AMD vs. Intel) and use the info to emit
   the correct hypercall instruction instead of relying on KVM to patch
   in VMMCALL
 
 - Use TAP interface for kvm_binary_stats_test and tsc_msrs_test
 -----BEGIN PGP SIGNATURE-----
 
 iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmP2YA0UHHBib256aW5p
 QHJlZGhhdC5jb20ACgkQv/vSX3jHroPg/Qf+J6nT+TkIa+8Ei+fN1oMTDp4YuIOx
 mXvJ9mRK9sQ+tAUVwvDz3qN/fK5mjsYbRHIDlVc5p2Q3bCrVGDDqXPFfCcLx1u+O
 9U9xjkO4JxD2LS9pc70FYOyzVNeJ8VMGOBbC2b0lkdYZ4KnUc6e/WWFKJs96bK+H
 duo+RIVyaMthnvbTwSv1K3qQb61n6lSJXplywS8KWFK6NZAmBiEFDAWGRYQE9lLs
 VcVcG0iDJNL/BQJ5InKCcvXVGskcCm9erDszPo7w4Bypa4S9AMS42DHUaRZrBJwV
 /WqdH7ckIz7+OSV0W1j+bKTHAFVTCjXYOM7wQykgjawjICzMSnnG9Gpskw==
 =goe1
 -----END PGP SIGNATURE-----

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "ARM:

   - Provide a virtual cache topology to the guest to avoid
     inconsistencies with migration on heterogenous systems. Non secure
     software has no practical need to traverse the caches by set/way in
     the first place

   - Add support for taking stage-2 access faults in parallel. This was
     an accidental omission in the original parallel faults
     implementation, but should provide a marginal improvement to
     machines w/o FEAT_HAFDBS (such as hardware from the fruit company)

   - A preamble to adding support for nested virtualization to KVM,
     including vEL2 register state, rudimentary nested exception
     handling and masking unsupported features for nested guests

   - Fixes to the PSCI relay that avoid an unexpected host SVE trap when
     resuming a CPU when running pKVM

   - VGIC maintenance interrupt support for the AIC

   - Improvements to the arch timer emulation, primarily aimed at
     reducing the trap overhead of running nested

   - Add CONFIG_USERFAULTFD to the KVM selftests config fragment in the
     interest of CI systems

   - Avoid VM-wide stop-the-world operations when a vCPU accesses its
     own redistributor

   - Serialize when toggling CPACR_EL1.SMEN to avoid unexpected
     exceptions in the host

   - Aesthetic and comment/kerneldoc fixes

   - Drop the vestiges of the old Columbia mailing list and add [Oliver]
     as co-maintainer

  RISC-V:

   - Fix wrong usage of PGDIR_SIZE instead of PUD_SIZE

   - Correctly place the guest in S-mode after redirecting a trap to the
     guest

   - Redirect illegal instruction traps to guest

   - SBI PMU support for guest

  s390:

   - Sort out confusion between virtual and physical addresses, which
     currently are the same on s390

   - A new ioctl that performs cmpxchg on guest memory

   - A few fixes

  x86:

   - Change tdp_mmu to a read-only parameter

   - Separate TDP and shadow MMU page fault paths

   - Enable Hyper-V invariant TSC control

   - Fix a variety of APICv and AVIC bugs, some of them real-world, some
     of them affecting architecurally legal but unlikely to happen in
     practice

   - Mark APIC timer as expired if its in one-shot mode and the count
     underflows while the vCPU task was being migrated

   - Advertise support for Intel's new fast REP string features

   - Fix a double-shootdown issue in the emergency reboot code

   - Ensure GIF=1 and disable SVM during an emergency reboot, i.e. give
     SVM similar treatment to VMX

   - Update Xen's TSC info CPUID sub-leaves as appropriate

   - Add support for Hyper-V's extended hypercalls, where "support" at
     this point is just forwarding the hypercalls to userspace

   - Clean up the kvm->lock vs. kvm->srcu sequences when updating the
     PMU and MSR filters

   - One-off fixes and cleanups

   - Fix and cleanup the range-based TLB flushing code, used when KVM is
     running on Hyper-V

   - Add support for filtering PMU events using a mask. If userspace
     wants to restrict heavily what events the guest can use, it can now
     do so without needing an absurd number of filter entries

   - Clean up KVM's handling of "PMU MSRs to save", especially when vPMU
     support is disabled

   - Add PEBS support for Intel Sapphire Rapids

   - Fix a mostly benign overflow bug in SEV's
     send|receive_update_data()

   - Move several SVM-specific flags into vcpu_svm

  x86 Intel:

   - Handle NMI VM-Exits before leaving the noinstr region

   - A few trivial cleanups in the VM-Enter flows

   - Stop enabling VMFUNC for L1 purely to document that KVM doesn't
     support EPTP switching (or any other VM function) for L1

   - Fix a crash when using eVMCS's enlighted MSR bitmaps

  Generic:

   - Clean up the hardware enable and initialization flow, which was
     scattered around multiple arch-specific hooks. Instead, just let
     the arch code call into generic code. Both x86 and ARM should
     benefit from not having to fight common KVM code's notion of how to
     do initialization

   - Account allocations in generic kvm_arch_alloc_vm()

   - Fix a memory leak if coalesced MMIO unregistration fails

  selftests:

   - On x86, cache the CPU vendor (AMD vs. Intel) and use the info to
     emit the correct hypercall instruction instead of relying on KVM to
     patch in VMMCALL

   - Use TAP interface for kvm_binary_stats_test and tsc_msrs_test"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (325 commits)
  KVM: SVM: hyper-v: placate modpost section mismatch error
  KVM: x86/mmu: Make tdp_mmu_allowed static
  KVM: arm64: nv: Use reg_to_encoding() to get sysreg ID
  KVM: arm64: nv: Only toggle cache for virtual EL2 when SCTLR_EL2 changes
  KVM: arm64: nv: Filter out unsupported features from ID regs
  KVM: arm64: nv: Emulate EL12 register accesses from the virtual EL2
  KVM: arm64: nv: Allow a sysreg to be hidden from userspace only
  KVM: arm64: nv: Emulate PSTATE.M for a guest hypervisor
  KVM: arm64: nv: Add accessors for SPSR_EL1, ELR_EL1 and VBAR_EL1 from virtual EL2
  KVM: arm64: nv: Handle SMCs taken from virtual EL2
  KVM: arm64: nv: Handle trapped ERET from virtual EL2
  KVM: arm64: nv: Inject HVC exceptions to the virtual EL2
  KVM: arm64: nv: Support virtual EL2 exceptions
  KVM: arm64: nv: Handle HCR_EL2.NV system register traps
  KVM: arm64: nv: Add nested virt VCPU primitives for vEL2 VCPU state
  KVM: arm64: nv: Add EL2 system registers to vcpu context
  KVM: arm64: nv: Allow userspace to set PSR_MODE_EL2x
  KVM: arm64: nv: Reset VCPU to EL2 registers if VCPU nested virt is set
  KVM: arm64: nv: Introduce nested virtualization VCPU feature
  KVM: arm64: Use the S2 MMU context to iterate over S2 table
  ...
2023-02-25 11:30:21 -08:00

718 lines
21 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* This file contains definitions from Hyper-V Hypervisor Top-Level Functional
* Specification (TLFS):
* https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs
*/
#ifndef _ASM_X86_HYPERV_TLFS_H
#define _ASM_X86_HYPERV_TLFS_H
#include <linux/types.h>
#include <asm/page.h>
/*
* The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
* is set by CPUID(HvCpuIdFunctionVersionAndFeatures).
*/
#define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS 0x40000000
#define HYPERV_CPUID_INTERFACE 0x40000001
#define HYPERV_CPUID_VERSION 0x40000002
#define HYPERV_CPUID_FEATURES 0x40000003
#define HYPERV_CPUID_ENLIGHTMENT_INFO 0x40000004
#define HYPERV_CPUID_IMPLEMENT_LIMITS 0x40000005
#define HYPERV_CPUID_CPU_MANAGEMENT_FEATURES 0x40000007
#define HYPERV_CPUID_NESTED_FEATURES 0x4000000A
#define HYPERV_CPUID_ISOLATION_CONFIG 0x4000000C
#define HYPERV_CPUID_VIRT_STACK_INTERFACE 0x40000081
#define HYPERV_VS_INTERFACE_EAX_SIGNATURE 0x31235356 /* "VS#1" */
#define HYPERV_CPUID_VIRT_STACK_PROPERTIES 0x40000082
/* Support for the extended IOAPIC RTE format */
#define HYPERV_VS_PROPERTIES_EAX_EXTENDED_IOAPIC_RTE BIT(2)
#define HYPERV_HYPERVISOR_PRESENT_BIT 0x80000000
#define HYPERV_CPUID_MIN 0x40000005
#define HYPERV_CPUID_MAX 0x4000ffff
/*
* Group D Features. The bit assignments are custom to each architecture.
* On x86/x64 these are HYPERV_CPUID_FEATURES.EDX bits.
*/
/* The MWAIT instruction is available (per section MONITOR / MWAIT) */
#define HV_X64_MWAIT_AVAILABLE BIT(0)
/* Guest debugging support is available */
#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1)
/* Performance Monitor support is available*/
#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2)
/* Support for physical CPU dynamic partitioning events is available*/
#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3)
/*
* Support for passing hypercall input parameter block via XMM
* registers is available
*/
#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4)
/* Support for a virtual guest idle state is available */
#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5)
/* Frequency MSRs available */
#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8)
/* Crash MSR available */
#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10)
/* Support for debug MSRs available */
#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11)
/* Support for extended gva ranges for flush hypercalls available */
#define HV_FEATURE_EXT_GVA_RANGES_FLUSH BIT(14)
/*
* Support for returning hypercall output block via XMM
* registers is available
*/
#define HV_X64_HYPERCALL_XMM_OUTPUT_AVAILABLE BIT(15)
/* stimer Direct Mode is available */
#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19)
/*
* Implementation recommendations. Indicates which behaviors the hypervisor
* recommends the OS implement for optimal performance.
* These are HYPERV_CPUID_ENLIGHTMENT_INFO.EAX bits.
*/
/*
* Recommend using hypercall for address space switches rather
* than MOV to CR3 instruction
*/
#define HV_X64_AS_SWITCH_RECOMMENDED BIT(0)
/* Recommend using hypercall for local TLB flushes rather
* than INVLPG or MOV to CR3 instructions */
#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED BIT(1)
/*
* Recommend using hypercall for remote TLB flushes rather
* than inter-processor interrupts
*/
#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED BIT(2)
/*
* Recommend using MSRs for accessing APIC registers
* EOI, ICR and TPR rather than their memory-mapped counterparts
*/
#define HV_X64_APIC_ACCESS_RECOMMENDED BIT(3)
/* Recommend using the hypervisor-provided MSR to initiate a system RESET */
#define HV_X64_SYSTEM_RESET_RECOMMENDED BIT(4)
/*
* Recommend using relaxed timing for this partition. If used,
* the VM should disable any watchdog timeouts that rely on the
* timely delivery of external interrupts
*/
#define HV_X64_RELAXED_TIMING_RECOMMENDED BIT(5)
/*
* Recommend not using Auto End-Of-Interrupt feature
*/
#define HV_DEPRECATING_AEOI_RECOMMENDED BIT(9)
/*
* Recommend using cluster IPI hypercalls.
*/
#define HV_X64_CLUSTER_IPI_RECOMMENDED BIT(10)
/* Recommend using the newer ExProcessorMasks interface */
#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED BIT(11)
/* Indicates that the hypervisor is nested within a Hyper-V partition. */
#define HV_X64_HYPERV_NESTED BIT(12)
/* Recommend using enlightened VMCS */
#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14)
/*
* CPU management features identification.
* These are HYPERV_CPUID_CPU_MANAGEMENT_FEATURES.EAX bits.
*/
#define HV_X64_START_LOGICAL_PROCESSOR BIT(0)
#define HV_X64_CREATE_ROOT_VIRTUAL_PROCESSOR BIT(1)
#define HV_X64_PERFORMANCE_COUNTER_SYNC BIT(2)
#define HV_X64_RESERVED_IDENTITY_BIT BIT(31)
/*
* Virtual processor will never share a physical core with another virtual
* processor, except for virtual processors that are reported as sibling SMT
* threads.
*/
#define HV_X64_NO_NONARCH_CORESHARING BIT(18)
/* Nested features. These are HYPERV_CPUID_NESTED_FEATURES.EAX bits. */
#define HV_X64_NESTED_DIRECT_FLUSH BIT(17)
#define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18)
#define HV_X64_NESTED_MSR_BITMAP BIT(19)
/* Nested features #2. These are HYPERV_CPUID_NESTED_FEATURES.EBX bits. */
#define HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL BIT(0)
/*
* This is specific to AMD and specifies that enlightened TLB flush is
* supported. If guest opts in to this feature, ASID invalidations only
* flushes gva -> hpa mapping entries. To flush the TLB entries derived
* from NPT, hypercalls should be used (HvFlushGuestPhysicalAddressSpace
* or HvFlushGuestPhysicalAddressList).
*/
#define HV_X64_NESTED_ENLIGHTENED_TLB BIT(22)
/* HYPERV_CPUID_ISOLATION_CONFIG.EAX bits. */
#define HV_PARAVISOR_PRESENT BIT(0)
/* HYPERV_CPUID_ISOLATION_CONFIG.EBX bits. */
#define HV_ISOLATION_TYPE GENMASK(3, 0)
#define HV_SHARED_GPA_BOUNDARY_ACTIVE BIT(5)
#define HV_SHARED_GPA_BOUNDARY_BITS GENMASK(11, 6)
enum hv_isolation_type {
HV_ISOLATION_TYPE_NONE = 0,
HV_ISOLATION_TYPE_VBS = 1,
HV_ISOLATION_TYPE_SNP = 2
};
/* Hyper-V specific model specific registers (MSRs) */
/* MSR used to identify the guest OS. */
#define HV_X64_MSR_GUEST_OS_ID 0x40000000
/* MSR used to setup pages used to communicate with the hypervisor. */
#define HV_X64_MSR_HYPERCALL 0x40000001
/* MSR used to provide vcpu index */
#define HV_REGISTER_VP_INDEX 0x40000002
/* MSR used to reset the guest OS. */
#define HV_X64_MSR_RESET 0x40000003
/* MSR used to provide vcpu runtime in 100ns units */
#define HV_X64_MSR_VP_RUNTIME 0x40000010
/* MSR used to read the per-partition time reference counter */
#define HV_REGISTER_TIME_REF_COUNT 0x40000020
/* A partition's reference time stamp counter (TSC) page */
#define HV_REGISTER_REFERENCE_TSC 0x40000021
/* MSR used to retrieve the TSC frequency */
#define HV_X64_MSR_TSC_FREQUENCY 0x40000022
/* MSR used to retrieve the local APIC timer frequency */
#define HV_X64_MSR_APIC_FREQUENCY 0x40000023
/* Define the virtual APIC registers */
#define HV_X64_MSR_EOI 0x40000070
#define HV_X64_MSR_ICR 0x40000071
#define HV_X64_MSR_TPR 0x40000072
#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073
/* Define synthetic interrupt controller model specific registers. */
#define HV_REGISTER_SCONTROL 0x40000080
#define HV_REGISTER_SVERSION 0x40000081
#define HV_REGISTER_SIEFP 0x40000082
#define HV_REGISTER_SIMP 0x40000083
#define HV_REGISTER_EOM 0x40000084
#define HV_REGISTER_SINT0 0x40000090
#define HV_REGISTER_SINT1 0x40000091
#define HV_REGISTER_SINT2 0x40000092
#define HV_REGISTER_SINT3 0x40000093
#define HV_REGISTER_SINT4 0x40000094
#define HV_REGISTER_SINT5 0x40000095
#define HV_REGISTER_SINT6 0x40000096
#define HV_REGISTER_SINT7 0x40000097
#define HV_REGISTER_SINT8 0x40000098
#define HV_REGISTER_SINT9 0x40000099
#define HV_REGISTER_SINT10 0x4000009A
#define HV_REGISTER_SINT11 0x4000009B
#define HV_REGISTER_SINT12 0x4000009C
#define HV_REGISTER_SINT13 0x4000009D
#define HV_REGISTER_SINT14 0x4000009E
#define HV_REGISTER_SINT15 0x4000009F
/*
* Define synthetic interrupt controller model specific registers for
* nested hypervisor.
*/
#define HV_REGISTER_NESTED_SCONTROL 0x40001080
#define HV_REGISTER_NESTED_SVERSION 0x40001081
#define HV_REGISTER_NESTED_SIEFP 0x40001082
#define HV_REGISTER_NESTED_SIMP 0x40001083
#define HV_REGISTER_NESTED_EOM 0x40001084
#define HV_REGISTER_NESTED_SINT0 0x40001090
/*
* Synthetic Timer MSRs. Four timers per vcpu.
*/
#define HV_REGISTER_STIMER0_CONFIG 0x400000B0
#define HV_REGISTER_STIMER0_COUNT 0x400000B1
#define HV_REGISTER_STIMER1_CONFIG 0x400000B2
#define HV_REGISTER_STIMER1_COUNT 0x400000B3
#define HV_REGISTER_STIMER2_CONFIG 0x400000B4
#define HV_REGISTER_STIMER2_COUNT 0x400000B5
#define HV_REGISTER_STIMER3_CONFIG 0x400000B6
#define HV_REGISTER_STIMER3_COUNT 0x400000B7
/* Hyper-V guest idle MSR */
#define HV_X64_MSR_GUEST_IDLE 0x400000F0
/* Hyper-V guest crash notification MSR's */
#define HV_REGISTER_CRASH_P0 0x40000100
#define HV_REGISTER_CRASH_P1 0x40000101
#define HV_REGISTER_CRASH_P2 0x40000102
#define HV_REGISTER_CRASH_P3 0x40000103
#define HV_REGISTER_CRASH_P4 0x40000104
#define HV_REGISTER_CRASH_CTL 0x40000105
/* TSC emulation after migration */
#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106
#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107
#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108
/* TSC invariant control */
#define HV_X64_MSR_TSC_INVARIANT_CONTROL 0x40000118
/* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */
#define HV_EXPOSE_INVARIANT_TSC BIT_ULL(0)
/* Register name aliases for temporary compatibility */
#define HV_X64_MSR_STIMER0_COUNT HV_REGISTER_STIMER0_COUNT
#define HV_X64_MSR_STIMER0_CONFIG HV_REGISTER_STIMER0_CONFIG
#define HV_X64_MSR_STIMER1_COUNT HV_REGISTER_STIMER1_COUNT
#define HV_X64_MSR_STIMER1_CONFIG HV_REGISTER_STIMER1_CONFIG
#define HV_X64_MSR_STIMER2_COUNT HV_REGISTER_STIMER2_COUNT
#define HV_X64_MSR_STIMER2_CONFIG HV_REGISTER_STIMER2_CONFIG
#define HV_X64_MSR_STIMER3_COUNT HV_REGISTER_STIMER3_COUNT
#define HV_X64_MSR_STIMER3_CONFIG HV_REGISTER_STIMER3_CONFIG
#define HV_X64_MSR_SCONTROL HV_REGISTER_SCONTROL
#define HV_X64_MSR_SVERSION HV_REGISTER_SVERSION
#define HV_X64_MSR_SIMP HV_REGISTER_SIMP
#define HV_X64_MSR_SIEFP HV_REGISTER_SIEFP
#define HV_X64_MSR_VP_INDEX HV_REGISTER_VP_INDEX
#define HV_X64_MSR_EOM HV_REGISTER_EOM
#define HV_X64_MSR_SINT0 HV_REGISTER_SINT0
#define HV_X64_MSR_SINT15 HV_REGISTER_SINT15
#define HV_X64_MSR_CRASH_P0 HV_REGISTER_CRASH_P0
#define HV_X64_MSR_CRASH_P1 HV_REGISTER_CRASH_P1
#define HV_X64_MSR_CRASH_P2 HV_REGISTER_CRASH_P2
#define HV_X64_MSR_CRASH_P3 HV_REGISTER_CRASH_P3
#define HV_X64_MSR_CRASH_P4 HV_REGISTER_CRASH_P4
#define HV_X64_MSR_CRASH_CTL HV_REGISTER_CRASH_CTL
#define HV_X64_MSR_TIME_REF_COUNT HV_REGISTER_TIME_REF_COUNT
#define HV_X64_MSR_REFERENCE_TSC HV_REGISTER_REFERENCE_TSC
/* Hyper-V memory host visibility */
enum hv_mem_host_visibility {
VMBUS_PAGE_NOT_VISIBLE = 0,
VMBUS_PAGE_VISIBLE_READ_ONLY = 1,
VMBUS_PAGE_VISIBLE_READ_WRITE = 3
};
/* HvCallModifySparseGpaPageHostVisibility hypercall */
#define HV_MAX_MODIFY_GPA_REP_COUNT ((PAGE_SIZE / sizeof(u64)) - 2)
struct hv_gpa_range_for_visibility {
u64 partition_id;
u32 host_visibility:2;
u32 reserved0:30;
u32 reserved1;
u64 gpa_page_list[HV_MAX_MODIFY_GPA_REP_COUNT];
} __packed;
/*
* Declare the MSR used to setup pages used to communicate with the hypervisor.
*/
union hv_x64_msr_hypercall_contents {
u64 as_uint64;
struct {
u64 enable:1;
u64 reserved:11;
u64 guest_physical_address:52;
} __packed;
};
union hv_vp_assist_msr_contents {
u64 as_uint64;
struct {
u64 enable:1;
u64 reserved:11;
u64 pfn:52;
} __packed;
};
struct hv_reenlightenment_control {
__u64 vector:8;
__u64 reserved1:8;
__u64 enabled:1;
__u64 reserved2:15;
__u64 target_vp:32;
} __packed;
struct hv_tsc_emulation_control {
__u64 enabled:1;
__u64 reserved:63;
} __packed;
struct hv_tsc_emulation_status {
__u64 inprogress:1;
__u64 reserved:63;
} __packed;
#define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001
#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12
#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \
(~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1))
#define HV_X64_MSR_CRASH_PARAMS \
(1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0))
#define HV_IPI_LOW_VECTOR 0x10
#define HV_IPI_HIGH_VECTOR 0xff
#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001
#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12
#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \
(~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
/* Hyper-V Enlightened VMCS version mask in nested features CPUID */
#define HV_X64_ENLIGHTENED_VMCS_VERSION 0xff
#define HV_X64_MSR_TSC_REFERENCE_ENABLE 0x00000001
#define HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT 12
/* Number of XMM registers used in hypercall input/output */
#define HV_HYPERCALL_MAX_XMM_REGISTERS 6
struct hv_nested_enlightenments_control {
struct {
__u32 directhypercall:1;
__u32 reserved:31;
} features;
struct {
__u32 inter_partition_comm:1;
__u32 reserved:31;
} hypercallControls;
} __packed;
/* Define virtual processor assist page structure. */
struct hv_vp_assist_page {
__u32 apic_assist;
__u32 reserved1;
__u32 vtl_entry_reason;
__u32 vtl_reserved;
__u64 vtl_ret_x64rax;
__u64 vtl_ret_x64rcx;
struct hv_nested_enlightenments_control nested_control;
__u8 enlighten_vmentry;
__u8 reserved2[7];
__u64 current_nested_vmcs;
__u8 synthetic_time_unhalted_timer_expired;
__u8 reserved3[7];
__u8 virtualization_fault_information[40];
__u8 reserved4[8];
__u8 intercept_message[256];
__u8 vtl_ret_actions[256];
} __packed;
struct hv_enlightened_vmcs {
u32 revision_id;
u32 abort;
u16 host_es_selector;
u16 host_cs_selector;
u16 host_ss_selector;
u16 host_ds_selector;
u16 host_fs_selector;
u16 host_gs_selector;
u16 host_tr_selector;
u16 padding16_1;
u64 host_ia32_pat;
u64 host_ia32_efer;
u64 host_cr0;
u64 host_cr3;
u64 host_cr4;
u64 host_ia32_sysenter_esp;
u64 host_ia32_sysenter_eip;
u64 host_rip;
u32 host_ia32_sysenter_cs;
u32 pin_based_vm_exec_control;
u32 vm_exit_controls;
u32 secondary_vm_exec_control;
u64 io_bitmap_a;
u64 io_bitmap_b;
u64 msr_bitmap;
u16 guest_es_selector;
u16 guest_cs_selector;
u16 guest_ss_selector;
u16 guest_ds_selector;
u16 guest_fs_selector;
u16 guest_gs_selector;
u16 guest_ldtr_selector;
u16 guest_tr_selector;
u32 guest_es_limit;
u32 guest_cs_limit;
u32 guest_ss_limit;
u32 guest_ds_limit;
u32 guest_fs_limit;
u32 guest_gs_limit;
u32 guest_ldtr_limit;
u32 guest_tr_limit;
u32 guest_gdtr_limit;
u32 guest_idtr_limit;
u32 guest_es_ar_bytes;
u32 guest_cs_ar_bytes;
u32 guest_ss_ar_bytes;
u32 guest_ds_ar_bytes;
u32 guest_fs_ar_bytes;
u32 guest_gs_ar_bytes;
u32 guest_ldtr_ar_bytes;
u32 guest_tr_ar_bytes;
u64 guest_es_base;
u64 guest_cs_base;
u64 guest_ss_base;
u64 guest_ds_base;
u64 guest_fs_base;
u64 guest_gs_base;
u64 guest_ldtr_base;
u64 guest_tr_base;
u64 guest_gdtr_base;
u64 guest_idtr_base;
u64 padding64_1[3];
u64 vm_exit_msr_store_addr;
u64 vm_exit_msr_load_addr;
u64 vm_entry_msr_load_addr;
u64 cr3_target_value0;
u64 cr3_target_value1;
u64 cr3_target_value2;
u64 cr3_target_value3;
u32 page_fault_error_code_mask;
u32 page_fault_error_code_match;
u32 cr3_target_count;
u32 vm_exit_msr_store_count;
u32 vm_exit_msr_load_count;
u32 vm_entry_msr_load_count;
u64 tsc_offset;
u64 virtual_apic_page_addr;
u64 vmcs_link_pointer;
u64 guest_ia32_debugctl;
u64 guest_ia32_pat;
u64 guest_ia32_efer;
u64 guest_pdptr0;
u64 guest_pdptr1;
u64 guest_pdptr2;
u64 guest_pdptr3;
u64 guest_pending_dbg_exceptions;
u64 guest_sysenter_esp;
u64 guest_sysenter_eip;
u32 guest_activity_state;
u32 guest_sysenter_cs;
u64 cr0_guest_host_mask;
u64 cr4_guest_host_mask;
u64 cr0_read_shadow;
u64 cr4_read_shadow;
u64 guest_cr0;
u64 guest_cr3;
u64 guest_cr4;
u64 guest_dr7;
u64 host_fs_base;
u64 host_gs_base;
u64 host_tr_base;
u64 host_gdtr_base;
u64 host_idtr_base;
u64 host_rsp;
u64 ept_pointer;
u16 virtual_processor_id;
u16 padding16_2[3];
u64 padding64_2[5];
u64 guest_physical_address;
u32 vm_instruction_error;
u32 vm_exit_reason;
u32 vm_exit_intr_info;
u32 vm_exit_intr_error_code;
u32 idt_vectoring_info_field;
u32 idt_vectoring_error_code;
u32 vm_exit_instruction_len;
u32 vmx_instruction_info;
u64 exit_qualification;
u64 exit_io_instruction_ecx;
u64 exit_io_instruction_esi;
u64 exit_io_instruction_edi;
u64 exit_io_instruction_eip;
u64 guest_linear_address;
u64 guest_rsp;
u64 guest_rflags;
u32 guest_interruptibility_info;
u32 cpu_based_vm_exec_control;
u32 exception_bitmap;
u32 vm_entry_controls;
u32 vm_entry_intr_info_field;
u32 vm_entry_exception_error_code;
u32 vm_entry_instruction_len;
u32 tpr_threshold;
u64 guest_rip;
u32 hv_clean_fields;
u32 padding32_1;
u32 hv_synthetic_controls;
struct {
u32 nested_flush_hypercall:1;
u32 msr_bitmap:1;
u32 reserved:30;
} __packed hv_enlightenments_control;
u32 hv_vp_id;
u32 padding32_2;
u64 hv_vm_id;
u64 partition_assist_page;
u64 padding64_4[4];
u64 guest_bndcfgs;
u64 guest_ia32_perf_global_ctrl;
u64 guest_ia32_s_cet;
u64 guest_ssp;
u64 guest_ia32_int_ssp_table_addr;
u64 guest_ia32_lbr_ctl;
u64 padding64_5[2];
u64 xss_exit_bitmap;
u64 encls_exiting_bitmap;
u64 host_ia32_perf_global_ctrl;
u64 tsc_multiplier;
u64 host_ia32_s_cet;
u64 host_ssp;
u64 host_ia32_int_ssp_table_addr;
u64 padding64_6;
} __packed;
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP BIT(0)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP BIT(1)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2 BIT(2)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1 BIT(3)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC BIT(4)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT BIT(5)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY BIT(6)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN BIT(7)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR BIT(8)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT BIT(9)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC BIT(10)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1 BIT(11)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2 BIT(12)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER BIT(13)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1 BIT(14)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL BIT(15)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF
/*
* Note, Hyper-V isn't actually stealing bit 28 from Intel, just abusing it by
* pairing it with architecturally impossible exit reasons. Bit 28 is set only
* on SMI exits to a SMI transfer monitor (STM) and if and only if a MTF VM-Exit
* is pending. I.e. it will never be set by hardware for non-SMI exits (there
* are only three), nor will it ever be set unless the VMM is an STM.
*/
#define HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH 0x10000031
/*
* Hyper-V uses the software reserved 32 bytes in VMCB control area to expose
* SVM enlightenments to guests.
*/
struct hv_vmcb_enlightenments {
struct __packed hv_enlightenments_control {
u32 nested_flush_hypercall:1;
u32 msr_bitmap:1;
u32 enlightened_npt_tlb: 1;
u32 reserved:29;
} __packed hv_enlightenments_control;
u32 hv_vp_id;
u64 hv_vm_id;
u64 partition_assist_page;
u64 reserved;
} __packed;
/*
* Hyper-V uses the software reserved clean bit in VMCB.
*/
#define HV_VMCB_NESTED_ENLIGHTENMENTS 31
/* Synthetic VM-Exit */
#define HV_SVM_EXITCODE_ENL 0xf0000000
#define HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH (1)
struct hv_partition_assist_pg {
u32 tlb_lock_count;
};
enum hv_interrupt_type {
HV_X64_INTERRUPT_TYPE_FIXED = 0x0000,
HV_X64_INTERRUPT_TYPE_LOWESTPRIORITY = 0x0001,
HV_X64_INTERRUPT_TYPE_SMI = 0x0002,
HV_X64_INTERRUPT_TYPE_REMOTEREAD = 0x0003,
HV_X64_INTERRUPT_TYPE_NMI = 0x0004,
HV_X64_INTERRUPT_TYPE_INIT = 0x0005,
HV_X64_INTERRUPT_TYPE_SIPI = 0x0006,
HV_X64_INTERRUPT_TYPE_EXTINT = 0x0007,
HV_X64_INTERRUPT_TYPE_LOCALINT0 = 0x0008,
HV_X64_INTERRUPT_TYPE_LOCALINT1 = 0x0009,
HV_X64_INTERRUPT_TYPE_MAXIMUM = 0x000A,
};
union hv_msi_address_register {
u32 as_uint32;
struct {
u32 reserved1:2;
u32 destination_mode:1;
u32 redirection_hint:1;
u32 reserved2:8;
u32 destination_id:8;
u32 msi_base:12;
};
} __packed;
union hv_msi_data_register {
u32 as_uint32;
struct {
u32 vector:8;
u32 delivery_mode:3;
u32 reserved1:3;
u32 level_assert:1;
u32 trigger_mode:1;
u32 reserved2:16;
};
} __packed;
/* HvRetargetDeviceInterrupt hypercall */
union hv_msi_entry {
u64 as_uint64;
struct {
union hv_msi_address_register address;
union hv_msi_data_register data;
} __packed;
};
#include <asm-generic/hyperv-tlfs.h>
#endif