diff options
28 files changed, 1563 insertions, 95 deletions
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index ffc350b649ad..6ae24c5ca559 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -2908,6 +2908,16 @@ such as set vcpu counter or reset vcpu, and they have the following id bit patte 0x9030 0000 0002 <reg:16> +x86 MSR registers have the following id bit patterns:: + 0x2030 0002 <msr number:32> + +Following are the KVM-defined registers for x86: + +======================= ========= ============================================= + Encoding Register Description +======================= ========= ============================================= + 0x2030 0003 0000 0000 SSP Shadow Stack Pointer +======================= ========= ============================================= 4.69 KVM_GET_ONE_REG -------------------- @@ -3588,7 +3598,7 @@ VCPU matching underlying host. --------------------- :Capability: basic -:Architectures: arm64, mips, riscv +:Architectures: arm64, mips, riscv, x86 (if KVM_CAP_ONE_REG) :Type: vcpu ioctl :Parameters: struct kvm_reg_list (in/out) :Returns: 0 on success; -1 on error @@ -3631,6 +3641,8 @@ Note that s390 does not support KVM_GET_REG_LIST for historical reasons - KVM_REG_S390_GBEA +Note, for x86, all MSRs enumerated by KVM_GET_MSR_INDEX_LIST are supported as +type KVM_X86_REG_TYPE_MSR, but are NOT enumerated via KVM_GET_REG_LIST. 4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated) ----------------------------------------- diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 9e611901d310..0eed9b430849 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -142,7 +142,7 @@ | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \ | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP \ - | X86_CR4_LAM_SUP)) + | X86_CR4_LAM_SUP | X86_CR4_CET)) #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) @@ -267,6 +267,7 @@ enum x86_intercept_stage; #define PFERR_RSVD_MASK BIT(3) #define PFERR_FETCH_MASK BIT(4) #define PFERR_PK_MASK BIT(5) +#define PFERR_SS_MASK BIT(6) #define PFERR_SGX_MASK BIT(15) #define PFERR_GUEST_RMP_MASK BIT_ULL(31) #define PFERR_GUEST_FINAL_MASK BIT_ULL(32) @@ -815,7 +816,6 @@ struct kvm_vcpu_arch { bool at_instruction_boundary; bool tpr_access_reporting; bool xfd_no_write_intercept; - u64 ia32_xss; u64 microcode_version; u64 arch_capabilities; u64 perf_capabilities; @@ -876,6 +876,8 @@ struct kvm_vcpu_arch { u64 xcr0; u64 guest_supported_xcr0; + u64 ia32_xss; + u64 guest_supported_xss; struct kvm_pio_request pio; void *pio_data; diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index cca7d6641287..c85c50019523 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -106,6 +106,7 @@ #define VM_EXIT_CLEAR_BNDCFGS 0x00800000 #define VM_EXIT_PT_CONCEAL_PIP 0x01000000 #define VM_EXIT_CLEAR_IA32_RTIT_CTL 0x02000000 +#define VM_EXIT_LOAD_CET_STATE 0x10000000 #define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR 0x00036dff @@ -119,6 +120,7 @@ #define VM_ENTRY_LOAD_BNDCFGS 0x00010000 #define VM_ENTRY_PT_CONCEAL_PIP 0x00020000 #define VM_ENTRY_LOAD_IA32_RTIT_CTL 0x00040000 +#define VM_ENTRY_LOAD_CET_STATE 0x00100000 #define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR 0x000011ff @@ -132,6 +134,7 @@ #define VMX_BASIC_DUAL_MONITOR_TREATMENT BIT_ULL(49) #define VMX_BASIC_INOUT BIT_ULL(54) #define VMX_BASIC_TRUE_CTLS BIT_ULL(55) +#define VMX_BASIC_NO_HW_ERROR_CODE_CC BIT_ULL(56) static inline u32 vmx_basic_vmcs_revision_id(u64 vmx_basic) { @@ -369,6 +372,9 @@ enum vmcs_field { GUEST_PENDING_DBG_EXCEPTIONS = 0x00006822, GUEST_SYSENTER_ESP = 0x00006824, GUEST_SYSENTER_EIP = 0x00006826, + GUEST_S_CET = 0x00006828, + GUEST_SSP = 0x0000682a, + GUEST_INTR_SSP_TABLE = 0x0000682c, HOST_CR0 = 0x00006c00, HOST_CR3 = 0x00006c02, HOST_CR4 = 0x00006c04, @@ -381,6 +387,9 @@ enum vmcs_field { HOST_IA32_SYSENTER_EIP = 0x00006c12, HOST_RSP = 0x00006c14, HOST_RIP = 0x00006c16, + HOST_S_CET = 0x00006c18, + HOST_SSP = 0x00006c1a, + HOST_INTR_SSP_TABLE = 0x00006c1c }; /* diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 0f15d683817d..d420c9c066d4 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -35,6 +35,11 @@ #define MC_VECTOR 18 #define XM_VECTOR 19 #define VE_VECTOR 20 +#define CP_VECTOR 21 + +#define HV_VECTOR 28 +#define VC_VECTOR 29 +#define SX_VECTOR 30 /* Select x86 specific features in <linux/kvm.h> */ #define __KVM_HAVE_PIT @@ -411,6 +416,35 @@ struct kvm_xcrs { __u64 padding[16]; }; +#define KVM_X86_REG_TYPE_MSR 2 +#define KVM_X86_REG_TYPE_KVM 3 + +#define KVM_X86_KVM_REG_SIZE(reg) \ +({ \ + reg == KVM_REG_GUEST_SSP ? KVM_REG_SIZE_U64 : 0; \ +}) + +#define KVM_X86_REG_TYPE_SIZE(type, reg) \ +({ \ + __u64 type_size = (__u64)type << 32; \ + \ + type_size |= type == KVM_X86_REG_TYPE_MSR ? KVM_REG_SIZE_U64 : \ + type == KVM_X86_REG_TYPE_KVM ? KVM_X86_KVM_REG_SIZE(reg) : \ + 0; \ + type_size; \ +}) + +#define KVM_X86_REG_ID(type, index) \ + (KVM_REG_X86 | KVM_X86_REG_TYPE_SIZE(type, index) | index) + +#define KVM_X86_REG_MSR(index) \ + KVM_X86_REG_ID(KVM_X86_REG_TYPE_MSR, index) +#define KVM_X86_REG_KVM(index) \ + KVM_X86_REG_ID(KVM_X86_REG_TYPE_KVM, index) + +/* KVM-defined registers starting from 0 */ +#define KVM_REG_GUEST_SSP 0 + #define KVM_SYNC_X86_REGS (1UL << 0) #define KVM_SYNC_X86_SREGS (1UL << 1) #define KVM_SYNC_X86_EVENTS (1UL << 2) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index efee08fad72e..d290dbc96831 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -263,6 +263,17 @@ static u64 cpuid_get_supported_xcr0(struct kvm_vcpu *vcpu) return (best->eax | ((u64)best->edx << 32)) & kvm_caps.supported_xcr0; } +static u64 cpuid_get_supported_xss(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry_index(vcpu, 0xd, 1); + if (!best) + return 0; + + return (best->ecx | ((u64)best->edx << 32)) & kvm_caps.supported_xss; +} + static __always_inline void kvm_update_feature_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entry, unsigned int x86_feature, @@ -305,7 +316,8 @@ static void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) best = kvm_find_cpuid_entry_index(vcpu, 0xD, 1); if (best && (cpuid_entry_has(best, X86_FEATURE_XSAVES) || cpuid_entry_has(best, X86_FEATURE_XSAVEC))) - best->ebx = xstate_required_size(vcpu->arch.xcr0, true); + best->ebx = xstate_required_size(vcpu->arch.xcr0 | + vcpu->arch.ia32_xss, true); } static bool kvm_cpuid_has_hyperv(struct kvm_vcpu *vcpu) @@ -424,6 +436,7 @@ void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) } vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu); + vcpu->arch.guest_supported_xss = cpuid_get_supported_xss(vcpu); vcpu->arch.pv_cpuid.features = kvm_apply_cpuid_pv_features_quirk(vcpu); @@ -933,6 +946,7 @@ void kvm_set_cpu_caps(void) VENDOR_F(WAITPKG), F(SGX_LC), F(BUS_LOCK_DETECT), + X86_64_F(SHSTK), ); /* @@ -942,6 +956,14 @@ void kvm_set_cpu_caps(void) if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) kvm_cpu_cap_clear(X86_FEATURE_PKU); + /* + * Shadow Stacks aren't implemented in the Shadow MMU. Shadow Stack + * accesses require "magic" Writable=0,Dirty=1 protection, which KVM + * doesn't know how to emulate or map. + */ + if (!tdp_enabled) + kvm_cpu_cap_clear(X86_FEATURE_SHSTK); + kvm_cpu_cap_init(CPUID_7_EDX, F(AVX512_4VNNIW), F(AVX512_4FMAPS), @@ -959,8 +981,19 @@ void kvm_set_cpu_caps(void) F(AMX_INT8), F(AMX_BF16), F(FLUSH_L1D), + F(IBT), ); + /* + * Disable support for IBT and SHSTK if KVM is configured to emulate + * accesses to reserved GPAs, as KVM's emulator doesn't support IBT or + * SHSTK, nor does KVM handle Shadow Stack #PFs (see above). + */ + if (allow_smaller_maxphyaddr) { + kvm_cpu_cap_clear(X86_FEATURE_SHSTK); + kvm_cpu_cap_clear(X86_FEATURE_IBT); + } + if (boot_cpu_has(X86_FEATURE_AMD_IBPB_RET) && boot_cpu_has(X86_FEATURE_AMD_IBPB) && boot_cpu_has(X86_FEATURE_AMD_IBRS)) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 23929151a5b8..59f93f68718a 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -178,6 +178,7 @@ #define IncSP ((u64)1 << 54) /* SP is incremented before ModRM calc */ #define TwoMemOp ((u64)1 << 55) /* Instruction has two memory operand */ #define IsBranch ((u64)1 << 56) /* Instruction is considered a branch. */ +#define ShadowStack ((u64)1 << 57) /* Instruction affects Shadow Stacks. */ #define DstXacc (DstAccLo | SrcAccHi | SrcWrite) @@ -1553,6 +1554,37 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, return linear_write_system(ctxt, addr, desc, sizeof(*desc)); } +static bool emulator_is_ssp_invalid(struct x86_emulate_ctxt *ctxt, u8 cpl) +{ + const u32 MSR_IA32_X_CET = cpl == 3 ? MSR_IA32_U_CET : MSR_IA32_S_CET; + u64 efer = 0, cet = 0, ssp = 0; + + if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_CET)) + return false; + + if (ctxt->ops->get_msr(ctxt, MSR_EFER, &efer)) + return true; + + /* SSP is guaranteed to be valid if the vCPU was already in 32-bit mode. */ + if (!(efer & EFER_LMA)) + return false; + + if (ctxt->ops->get_msr(ctxt, MSR_IA32_X_CET, &cet)) + return true; + + if (!(cet & CET_SHSTK_EN)) + return false; + + if (ctxt->ops->get_msr(ctxt, MSR_KVM_INTERNAL_GUEST_SSP, &ssp)) + return true; + + /* + * On transfer from 64-bit mode to compatibility mode, SSP[63:32] must + * be 0, i.e. SSP must be a 32-bit value outside of 64-bit mode. + */ + return ssp >> 32; +} + static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, int seg, u8 cpl, enum x86_transfer_type transfer, @@ -1693,6 +1725,10 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, if (efer & EFER_LMA) goto exception; } + if (!seg_desc.l && emulator_is_ssp_invalid(ctxt, cpl)) { + err_code = 0; + goto exception; + } /* CS(RPL) <- CPL */ selector = (selector & 0xfffc) | cpl; @@ -4068,8 +4104,8 @@ static const struct opcode group4[] = { static const struct opcode group5[] = { F(DstMem | SrcNone | Lock, em_inc), F(DstMem | SrcNone | Lock, em_dec), - I(SrcMem | NearBranch | IsBranch, em_call_near_abs), - I(SrcMemFAddr | ImplicitOps | IsBranch, em_call_far), + I(SrcMem | NearBranch | IsBranch | ShadowStack, em_call_near_abs), + I(SrcMemFAddr | ImplicitOps | IsBranch | ShadowStack, em_call_far), I(SrcMem | NearBranch | IsBranch, em_jmp_abs), I(SrcMemFAddr | ImplicitOps | IsBranch, em_jmp_far), I(SrcMem | Stack | TwoMemOp, em_push), D(Undefined), @@ -4304,7 +4340,7 @@ static const struct opcode opcode_table[256] = { DI(SrcAcc | DstReg, pause), X7(D(SrcAcc | DstReg)), /* 0x98 - 0x9F */ D(DstAcc | SrcNone), I(ImplicitOps | SrcAcc, em_cwd), - I(SrcImmFAddr | No64 | IsBranch, em_call_far), N, + I(SrcImmFAddr | No64 | IsBranch | ShadowStack, em_call_far), N, II(ImplicitOps | Stack, em_pushf, pushf), II(ImplicitOps | Stack, em_popf, popf), I(ImplicitOps, em_sahf), I(ImplicitOps, em_lahf), @@ -4324,19 +4360,19 @@ static const struct opcode opcode_table[256] = { X8(I(DstReg | SrcImm64 | Mov, em_mov)), /* 0xC0 - 0xC7 */ G(ByteOp | Src2ImmByte, group2), G(Src2ImmByte, group2), - I(ImplicitOps | NearBranch | SrcImmU16 | IsBranch, em_ret_near_imm), - I(ImplicitOps | NearBranch | IsBranch, em_ret), + I(ImplicitOps | NearBranch | SrcImmU16 | IsBranch | ShadowStack, em_ret_near_imm), + I(ImplicitOps | NearBranch | IsBranch | ShadowStack, em_ret), I(DstReg | SrcMemFAddr | ModRM | No64 | Src2ES, em_lseg), I(DstReg | SrcMemFAddr | ModRM | No64 | Src2DS, em_lseg), G(ByteOp, group11), G(0, group11), /* 0xC8 - 0xCF */ I(Stack | SrcImmU16 | Src2ImmByte, em_enter), I(Stack, em_leave), - I(ImplicitOps | SrcImmU16 | IsBranch, em_ret_far_imm), - I(ImplicitOps | IsBranch, em_ret_far), - D(ImplicitOps | IsBranch), DI(SrcImmByte | IsBranch, intn), + I(ImplicitOps | SrcImmU16 | IsBranch | ShadowStack, em_ret_far_imm), + I(ImplicitOps | IsBranch | ShadowStack, em_ret_far), + D(ImplicitOps | IsBranch), DI(SrcImmByte | IsBranch | ShadowStack, intn), D(ImplicitOps | No64 | IsBranch), - II(ImplicitOps | IsBranch, em_iret, iret), + II(ImplicitOps | IsBranch | ShadowStack, em_iret, iret), /* 0xD0 - 0xD7 */ G(Src2One | ByteOp, group2), G(Src2One, group2), G(Src2CL | ByteOp, group2), G(Src2CL, group2), @@ -4352,7 +4388,7 @@ static const struct opcode opcode_table[256] = { I2bvIP(SrcImmUByte | DstAcc, em_in, in, check_perm_in), I2bvIP(SrcAcc | DstImmUByte, em_out, out, check_perm_out), /* 0xE8 - 0xEF */ - I(SrcImm | NearBranch | IsBranch, em_call), + I(SrcImm | NearBranch | IsBranch | ShadowStack, em_call), D(SrcImm | ImplicitOps | NearBranch | IsBranch), I(SrcImmFAddr | No64 | IsBranch, em_jmp_far), D(SrcImmByte | ImplicitOps | NearBranch | IsBranch), @@ -4371,7 +4407,7 @@ static const struct opcode opcode_table[256] = { static const struct opcode twobyte_table[256] = { /* 0x00 - 0x0F */ G(0, group6), GD(0, &group7), N, N, - N, I(ImplicitOps | EmulateOnUD | IsBranch, em_syscall), + N, I(ImplicitOps | EmulateOnUD | IsBranch | ShadowStack, em_syscall), II(ImplicitOps | Priv, em_clts, clts), N, DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N, N, D(ImplicitOps | ModRM | SrcMem | NoAccess), N, N, @@ -4402,8 +4438,8 @@ static const struct opcode twobyte_table[256] = { IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc), II(ImplicitOps | Priv, em_rdmsr, rdmsr), IIP(ImplicitOps, em_rdpmc, rdpmc, check_rdpmc), - I(ImplicitOps | EmulateOnUD | IsBranch, em_sysenter), - I(ImplicitOps | Priv | EmulateOnUD | IsBranch, em_sysexit), + I(ImplicitOps | EmulateOnUD | IsBranch | ShadowStack, em_sysenter), + I(ImplicitOps | Priv | EmulateOnUD | IsBranch | ShadowStack, em_sysexit), N, N, N, N, N, N, N, N, N, N, /* 0x40 - 0x4F */ @@ -4514,6 +4550,60 @@ static const struct opcode opcode_map_0f_38[256] = { #undef I2bvIP #undef I6ALU +static bool is_shstk_instruction(struct x86_emulate_ctxt *ctxt) +{ + return ctxt->d & ShadowStack; +} + +static bool is_ibt_instruction(struct x86_emulate_ctxt *ctxt) +{ + u64 flags = ctxt->d; + + if (!(flags & IsBranch)) + return false; + + /* + * All far JMPs and CALLs (including SYSCALL, SYSENTER, and INTn) are + * indirect and thus affect IBT state. All far RETs (including SYSEXIT + * and IRET) are protected via Shadow Stacks and thus don't affect IBT + * state. IRET #GPs when returning to virtual-8086 and IBT or SHSTK is + * enabled, but that should be handled by IRET emulation (in the very + * unlikely scenario that KVM adds support for fully emulating IRET). + */ + if (!(flags & NearBranch)) + return ctxt->execute != em_iret && + ctxt->execute != em_ret_far && + ctxt->execute != em_ret_far_imm && + ctxt->execute != em_sysexit; + + switch (flags & SrcMask) { + case SrcReg: + case SrcMem: + case SrcMem16: + case SrcMem32: + return true; + case SrcMemFAddr: + case SrcImmFAddr: + /* Far branches should be handled above. */ + WARN_ON_ONCE(1); + return true; + case SrcNone: + case SrcImm: + case SrcImmByte: + /* + * Note, ImmU16 is used only for the stack adjustment operand on ENTER + * and RET instructions. ENTER isn't a branch and RET FAR is handled + * by the NearBranch check above. RET itself isn't an indirect branch. + */ + case SrcImmU16: + return false; + default: + WARN_ONCE(1, "Unexpected Src operand '%llx' on branch", + flags & SrcMask); + return false; + } +} + static unsigned imm_size(struct x86_emulate_ctxt *ctxt) { unsigned size; @@ -4943,6 +5033,40 @@ done_prefixes: ctxt->execute = opcode.u.execute; + /* + * Reject emulation if KVM might need to emulate shadow stack updates + * and/or indirect branch tracking enforcement, which the emulator + * doesn't support. + */ + if ((is_ibt_instruction(ctxt) || is_shstk_instruction(ctxt)) && + ctxt->ops->get_cr(ctxt, 4) & X86_CR4_CET) { + u64 u_cet = 0, s_cet = 0; + + /* + * Check both User and Supervisor on far transfers as inter- + * privilege level transfers are impacted by CET at the target + * privilege level, and that is not known at this time. The + * expectation is that the guest will not require emulation of + * any CET-affected instructions at any privilege level. + */ + if (!(ctxt->d & NearBranch)) + u_cet = s_cet = CET_SHSTK_EN | CET_ENDBR_EN; + else if (ctxt->ops->cpl(ctxt) == 3) + u_cet = CET_SHSTK_EN | CET_ENDBR_EN; + else + s_cet = CET_SHSTK_EN | CET_ENDBR_EN; + + if ((u_cet && ctxt->ops->get_msr(ctxt, MSR_IA32_U_CET, &u_cet)) || + (s_cet && ctxt->ops->get_msr(ctxt, MSR_IA32_S_CET, &s_cet))) + return EMULATION_FAILED; + + if ((u_cet | s_cet) & CET_SHSTK_EN && is_shstk_instruction(ctxt)) + return EMULATION_FAILED; + + if ((u_cet | s_cet) & CET_ENDBR_EN && is_ibt_instruction(ctxt)) + return EMULATION_FAILED; + } + if (unlikely(emulation_type & EMULTYPE_TRAP_UD) && likely(!(ctxt->d & EmulateOnUD))) return EMULATION_FAILED; diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 36a8786db291..8ddb01191d6f 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -7,7 +7,8 @@ #define KVM_POSSIBLE_CR0_GUEST_BITS (X86_CR0_TS | X86_CR0_WP) #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) + | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE \ + | X86_CR4_CET) #define X86_CR0_PDPTR_BITS (X86_CR0_CD | X86_CR0_NW | X86_CR0_PG) #define X86_CR4_TLBFLUSH_BITS (X86_CR4_PGE | X86_CR4_PCIDE | X86_CR4_PAE | X86_CR4_SMEP) diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index b4b6860ab971..f63074048ec6 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -212,7 +212,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, fault = (mmu->permissions[index] >> pte_access) & 1; - WARN_ON(pfec & (PFERR_PK_MASK | PFERR_RSVD_MASK)); + WARN_ON_ONCE(pfec & (PFERR_PK_MASK | PFERR_SS_MASK | PFERR_RSVD_MASK)); if (unlikely(mmu->pkru_mask)) { u32 pkru_bits, offset; diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index f35a830ce469..764e3015d021 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -51,6 +51,9 @@ { PFERR_PRESENT_MASK, "P" }, \ { PFERR_WRITE_MASK, "W" }, \ { PFERR_USER_MASK, "U" }, \ + { PFERR_PK_MASK, "PK" }, \ + { PFERR_SS_MASK, "SS" }, \ + { PFERR_SGX_MASK, "SGX" }, \ { PFERR_RSVD_MASK, "RSVD" }, \ { PFERR_FETCH_MASK, "F" } diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index 5dd8a1646800..b0b14ba37f9a 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -269,6 +269,10 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS); smram->int_shadow = kvm_x86_call(get_interrupt_shadow)(vcpu); + + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) && + kvm_msr_read(vcpu, MSR_KVM_INTERNAL_GUEST_SSP, &smram->ssp)) + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); } #endif @@ -558,6 +562,10 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, kvm_x86_call(set_interrupt_shadow)(vcpu, 0); ctxt->interruptibility = (u8)smstate->int_shadow; + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) && + kvm_msr_write(vcpu, MSR_KVM_INTERNAL_GUEST_SSP, smstate->ssp)) + return X86EMUL_UNHANDLEABLE; + return X86EMUL_CONTINUE; } #endif diff --git a/arch/x86/kvm/smm.h b/arch/x86/kvm/smm.h index 551703fbe200..db3c88f16138 100644 --- a/arch/x86/kvm/smm.h +++ b/arch/x86/kvm/smm.h @@ -116,8 +116,8 @@ struct kvm_smram_state_64 { u32 smbase; u32 reserved4[5]; - /* ssp and svm_* fields below are not implemented by KVM */ u64 ssp; + /* svm_* fields below are not implemented by KVM */ u64 svm_guest_pat; u64 svm_host_efer; u64 svm_host_cr4; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 826473f2d7c7..a6443feab252 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -636,6 +636,14 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 vmcb_mark_dirty(vmcb02, VMCB_DT); } + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) && + (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_CET)))) { + vmcb02->save.s_cet = vmcb12->save.s_cet; + vmcb02->save.isst_addr = vmcb12->save.isst_addr; + vmcb02->save.ssp = vmcb12->save.ssp; + vmcb_mark_dirty(vmcb02, VMCB_CET); + } + kvm_set_rflags(vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); svm_set_efer(vcpu, svm->nested.save.efer); @@ -1044,6 +1052,12 @@ void svm_copy_vmrun_state(struct vmcb_save_area *to_save, to_save->rsp = from_save->rsp; to_save->rip = from_save->rip; to_save->cpl = 0; + + if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) { + to_save->s_cet = from_save->s_cet; + to_save->isst_addr = from_save->isst_addr; + to_save->ssp = from_save->ssp; + } } void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb) @@ -1111,6 +1125,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm) vmcb12->save.dr6 = svm->vcpu.arch.dr6; vmcb12->save.cpl = vmcb02->save.cpl; + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) { + vmcb12->save.s_cet = vmcb02->save.s_cet; + vmcb12->save.isst_addr = vmcb02->save.isst_addr; + vmcb12->save.ssp = vmcb02->save.ssp; + } + vmcb12->control.int_state = vmcb02->control.int_state; vmcb12->control.exit_code = vmcb02->control.exit_code; vmcb12->control.exit_code_hi = vmcb02->control.exit_code_hi; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index aacfbffa3af5..0835c664fbfd 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -3354,6 +3354,9 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) if (kvm_ghcb_xcr0_is_valid(svm)) __kvm_set_xcr(vcpu, 0, kvm_ghcb_get_xcr0(svm)); + if (kvm_ghcb_xss_is_valid(svm)) + __kvm_emulate_msr_write(vcpu, MSR_IA32_XSS, kvm_ghcb_get_xss(svm)); + /* Copy the GHCB exit information into the VMCB fields */ exit_code = kvm_ghcb_get_sw_exit_code(svm); control->exit_code = lower_32_bits(exit_code); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 81db26b2a1bd..153c12dbf3eb 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -775,6 +775,17 @@ static void svm_recalc_msr_intercepts(struct kvm_vcpu *vcpu) svm_disable_intercept_for_msr(vcpu, MSR_IA32_MPERF, MSR_TYPE_R); } + if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) { + bool shstk_enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK); + + svm_set_intercept_for_msr(vcpu, MSR_IA32_U_CET, MSR_TYPE_RW, !shstk_enabled); + svm_set_intercept_for_msr(vcpu, MSR_IA32_S_CET, MSR_TYPE_RW, !shstk_enabled); + svm_set_intercept_for_msr(vcpu, MSR_IA32_PL0_SSP, MSR_TYPE_RW, !shstk_enabled); + svm_set_intercept_for_msr(vcpu, MSR_IA32_PL1_SSP, MSR_TYPE_RW, !shstk_enabled); + svm_set_intercept_for_msr(vcpu, MSR_IA32_PL2_SSP, MSR_TYPE_RW, !shstk_enabled); + svm_set_intercept_for_msr(vcpu, MSR_IA32_PL3_SSP, MSR_TYPE_RW, !shstk_enabled); + } + if (sev_es_guest(vcpu->kvm)) sev_es_recalc_msr_intercepts(vcpu); @@ -2641,8 +2652,8 @@ static int svm_get_feature_msr(u32 msr, u64 *data) static bool sev_es_prevent_msr_access(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - return sev_es_guest(vcpu->kvm) && - vcpu->arch.guest_state_protected && + return sev_es_guest(vcpu->kvm) && vcpu->arch.guest_state_protected && + msr_info->index != MSR_IA32_XSS && !msr_write_intercepted(vcpu, msr_info->index); } @@ -2698,6 +2709,15 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (guest_cpuid_is_intel_compatible(vcpu)) msr_info->data |= (u64)svm->sysenter_esp_hi << 32; break; + case MSR_IA32_S_CET: + msr_info->data = svm->vmcb->save.s_cet; + break; + case MSR_IA32_INT_SSP_TAB: + msr_info->data = svm->vmcb->save.isst_addr; + break; + case MSR_KVM_INTERNAL_GUEST_SSP: + msr_info->data = svm->vmcb->save.ssp; + break; case MSR_TSC_AUX: msr_info->data = svm->tsc_aux; break; @@ -2930,6 +2950,18 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->vmcb01.ptr->save.sysenter_esp = (u32)data; svm->sysenter_esp_hi = guest_cpuid_is_intel_compatible(vcpu) ? (data >> 32) : 0; break; + case MSR_IA32_S_CET: + svm->vmcb->save.s_cet = data; + vmcb_mark_dirty(svm->vmcb01.ptr, VMCB_CET); + break; + case MSR_IA32_INT_SSP_TAB: + svm->vmcb->save.isst_addr = data; + vmcb_mark_dirty(svm->vmcb01.ptr, VMCB_CET); + break; + case MSR_KVM_INTERNAL_GUEST_SSP: + svm->vmcb->save.ssp = data; + vmcb_mark_dirty(svm->vmcb01.ptr, VMCB_CET); + break; case MSR_TSC_AUX: /* * TSC_AUX is always virtualized for SEV-ES guests when the @@ -3320,6 +3352,10 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) pr_err("%-15s %016llx %-13s %016llx\n", "rsp:", save->rsp, "rax:", save->rax); pr_err("%-15s %016llx %-13s %016llx\n", + "s_cet:", save->s_cet, "ssp:", save->ssp); + pr_err("%-15s %016llx\n", + "isst_addr:", save->isst_addr); + pr_err("%-15s %016llx %-13s %016llx\n", "star:", save01->star, "lstar:", save01->lstar); pr_err("%-15s %016llx %-13s %016llx\n", "cstar:", save01->cstar, "sfmask:", save01->sfmask); @@ -3344,6 +3380,13 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) "sev_features", vmsa->sev_features); pr_err("%-15s %016llx %-13s %016llx\n", + "pl0_ssp:", vmsa->pl0_ssp, "pl1_ssp:", vmsa->pl1_ssp); + pr_err("%-15s %016llx %-13s %016llx\n", + "pl2_ssp:", vmsa->pl2_ssp, "pl3_ssp:", vmsa->pl3_ssp); + pr_err("%-15s %016llx\n", + "u_cet:", vmsa->u_cet); + + pr_err("%-15s %016llx %-13s %016llx\n", "rax:", vmsa->rax, "rbx:", vmsa->rbx); pr_err("%-15s %016llx %-13s %016llx\n", "rcx:", vmsa->rcx, "rdx:", vmsa->rdx); @@ -5149,7 +5192,8 @@ static __init void svm_set_cpu_caps(void) kvm_set_cpu_caps(); kvm_caps.supported_perf_cap = 0; - kvm_caps.supported_xss = 0; + + kvm_cpu_cap_clear(X86_FEATURE_IBT); /* CPUID 0x80000001 and 0x8000000A (SVM features) */ if (nested) { @@ -5299,6 +5343,21 @@ static __init int svm_hardware_setup(void) get_npt_level(), PG_LEVEL_1G); pr_info("Nested Paging %s\n", str_enabled_disabled(npt_enabled)); + /* + * It seems that on AMD processors PTE's accessed bit is + * being set by the CPU hardware before the NPF vmexit. + * This is not expected behaviour and our tests fail because + * of it. + * A workaround here is to disable support for + * GUEST_MAXPHYADDR < HOST_MAXPHYADDR if NPT is enabled. + * In this case userspace can know if there is support using + * KVM_CAP_SMALLER_MAXPHYADDR extension and decide how to handle + * it + * If future AMD CPU models change the behaviour described above, + * this variable can be changed accordingly + */ + allow_smaller_maxphyaddr = !npt_enabled; + /* Setup shadow_me_value and shadow_me_mask */ kvm_mmu_set_me_spte_mask(sme_me_mask, sme_me_mask); @@ -5375,21 +5434,6 @@ static __init int svm_hardware_setup(void) svm_set_cpu_caps(); - /* - * It seems that on AMD processors PTE's accessed bit is - * being set by the CPU hardware before the NPF vmexit. - * This is not expected behaviour and our tests fail because - * of it. - * A workaround here is to disable support for - * GUEST_MAXPHYADDR < HOST_MAXPHYADDR if NPT is enabled. - * In this case userspace can know if there is support using - * KVM_CAP_SMALLER_MAXPHYADDR extension and decide how to handle - * it - * If future AMD CPU models change the behaviour described above, - * this variable can be changed accordingly - */ - allow_smaller_maxphyaddr = !npt_enabled; - kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_CD_NW_CLEARED; return 0; diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 9526bb112b29..e4b04f435b3d 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -77,6 +77,7 @@ enum { * AVIC PHYSICAL_TABLE pointer, * AVIC LOGICAL_TABLE pointer */ + VMCB_CET, /* S_CET, SSP, ISST_ADDR */ VMCB_SW = 31, /* Reserved for hypervisor/software use */ }; @@ -85,7 +86,7 @@ enum { (1U << VMCB_ASID) | (1U << VMCB_INTR) | \ (1U << VMCB_NPT) | (1U << VMCB_CR) | (1U << VMCB_DR) | \ (1U << VMCB_DT) | (1U << VMCB_SEG) | (1U << VMCB_CR2) | \ - (1U << VMCB_LBR) | (1U << VMCB_AVIC) | \ + (1U << VMCB_LBR) | (1U << VMCB_AVIC) | (1U << VMCB_CET) | \ (1U << VMCB_SW)) /* TPR and CR2 are always written before VMRUN */ @@ -942,5 +943,6 @@ DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_1) DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_2) DEFINE_KVM_GHCB_ACCESSORS(sw_scratch) DEFINE_KVM_GHCB_ACCESSORS(xcr0) +DEFINE_KVM_GHCB_ACCESSORS(xss) #endif diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 57d79fd31df0..e79bc9cb7162 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -461,8 +461,9 @@ TRACE_EVENT(kvm_inj_virq, #define kvm_trace_sym_exc \ EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM), \ - EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), \ - EXS(MF), EXS(AC), EXS(MC) + EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), EXS(MF), \ + EXS(AC), EXS(MC), EXS(XM), EXS(VE), EXS(CP), \ + EXS(HV), EXS(VC), EXS(SX) /* * Tracepoint for kvm interrupt injection: diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index f614428dbeda..02aadb9d730e 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -73,6 +73,11 @@ static inline bool cpu_has_vmx_basic_inout(void) return vmcs_config.basic & VMX_BASIC_INOUT; } +static inline bool cpu_has_vmx_basic_no_hw_errcode_cc(void) +{ + return vmcs_config.basic & VMX_BASIC_NO_HW_ERROR_CODE_CC; +} + static inline bool cpu_has_virtual_nmis(void) { return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS && @@ -100,6 +105,10 @@ static inline bool cpu_has_load_perf_global_ctrl(void) return vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; } +static inline bool cpu_has_load_cet_ctrl(void) +{ + return (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_CET_STATE); +} static inline bool cpu_has_vmx_mpx(void) { return vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_BNDCFGS; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 2156c9a854f4..76271962cb70 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -721,6 +721,24 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_MPERF, MSR_TYPE_R); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_U_CET, MSR_TYPE_RW); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_S_CET, MSR_TYPE_RW); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PL0_SSP, MSR_TYPE_RW); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PL1_SSP, MSR_TYPE_RW); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PL2_SSP, MSR_TYPE_RW); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PL3_SSP, MSR_TYPE_RW); + kvm_vcpu_unmap(vcpu, &map); vmx->nested.force_msr_bitmap_recalc = false; @@ -1272,9 +1290,10 @@ static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data) { const u64 feature_bits = VMX_BASIC_DUAL_MONITOR_TREATMENT | VMX_BASIC_INOUT | - VMX_BASIC_TRUE_CTLS; + VMX_BASIC_TRUE_CTLS | + VMX_BASIC_NO_HW_ERROR_CODE_CC; - const u64 reserved_bits = GENMASK_ULL(63, 56) | + const u64 reserved_bits = GENMASK_ULL(63, 57) | GENMASK_ULL(47, 45) | BIT_ULL(31); @@ -2520,6 +2539,32 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 } } +static void vmcs_read_cet_state(struct kvm_vcpu *vcpu, u64 *s_cet, + u64 *ssp, u64 *ssp_tbl) +{ + if (guest_cpu_cap_has(vcpu, X86_FEATURE_IBT) || + guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) + *s_cet = vmcs_readl(GUEST_S_CET); + + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) { + *ssp = vmcs_readl(GUEST_SSP); + *ssp_tbl = vmcs_readl(GUEST_INTR_SSP_TABLE); + } +} + +static void vmcs_write_cet_state(struct kvm_vcpu *vcpu, u64 s_cet, + u64 ssp, u64 ssp_tbl) +{ + if (guest_cpu_cap_has(vcpu, X86_FEATURE_IBT) || + guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) + vmcs_writel(GUEST_S_CET, s_cet); + + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) { + vmcs_writel(GUEST_SSP, ssp); + vmcs_writel(GUEST_INTR_SSP_TABLE, ssp_tbl); + } +} + static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { struct hv_enlightened_vmcs *hv_evmcs = nested_vmx_evmcs(vmx); @@ -2636,6 +2681,10 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE) + vmcs_write_cet_state(&vmx->vcpu, vmcs12->guest_s_cet, + vmcs12->guest_ssp, vmcs12->guest_ssp_tbl); + set_cr4_guest_host_mask(vmx); } @@ -2675,6 +2724,13 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, kvm_set_dr(vcpu, 7, vcpu->arch.dr7); vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl); } + + if (!vmx->nested.nested_run_pending || + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE)) + vmcs_write_cet_state(vcpu, vmx->nested.pre_vmenter_s_cet, + vmx->nested.pre_vmenter_ssp, + vmx->nested.pre_vmenter_ssp_tbl); + if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) vmcs_write64(GUEST_BNDCFGS, vmx->nested.pre_vmenter_bndcfgs); @@ -2949,7 +3005,6 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, u8 vector = intr_info & INTR_INFO_VECTOR_MASK; u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK; bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK; - bool should_have_error_code; bool urg = nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST); bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE; @@ -2966,12 +3021,19 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, CC(intr_type == INTR_TYPE_OTHER_EVENT && vector != 0)) return -EINVAL; - /* VM-entry interruption-info field: deliver error code */ - should_have_error_code = - intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode && - x86_exception_has_error_code(vector); - if (CC(has_error_code != should_have_error_code)) - return -EINVAL; + /* + * Cannot deliver error code in real mode or if the interrupt + * type is not hardware exception. For other cases, do the + * consistency check only if the vCPU doesn't enumerate + * VMX_BASIC_NO_HW_ERROR_CODE_CC. + */ + if (!prot_mode || intr_type != INTR_TYPE_HARD_EXCEPTION) { + if (CC(has_error_code)) + return -EINVAL; + } else if (!nested_cpu_has_no_hw_errcode_cc(vcpu)) { + if (CC(has_error_code != x86_exception_has_error_code(vector))) + return -EINVAL; + } /* VM-entry exception error code */ if (CC(has_error_code && @@ -3038,6 +3100,16 @@ static bool is_l1_noncanonical_address_on_vmexit(u64 la, struct vmcs12 *vmcs12) return !__is_canonical_address(la, l1_address_bits_on_exit); } +static int nested_vmx_check_cet_state_common(struct kvm_vcpu *vcpu, u64 s_cet, + u64 ssp, u64 ssp_tbl) +{ + if (CC(!kvm_is_valid_u_s_cet(vcpu, s_cet)) || CC(!IS_ALIGNED(ssp, 4)) || + CC(is_noncanonical_msr_address(ssp_tbl, vcpu))) + return -EINVAL; + + return 0; +} + static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -3048,6 +3120,9 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3))) return -EINVAL; + if (CC(vmcs12->host_cr4 & X86_CR4_CET && !(vmcs12->host_cr0 & X86_CR0_WP))) + return -EINVAL; + if (CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_eip, vcpu))) return -EINVAL; @@ -3104,6 +3179,27 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, return -EINVAL; } + if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_CET_STATE) { + if (nested_vmx_check_cet_state_common(vcpu, vmcs12->host_s_cet, + vmcs12->host_ssp, + vmcs12->host_ssp_tbl)) + return -EINVAL; + + /* + * IA32_S_CET and SSP must be canonical if the host will + * enter 64-bit mode after VM-exit; otherwise, higher + * 32-bits must be all 0s. + */ + if (ia32e) { + if (CC(is_noncanonical_msr_address(vmcs12->host_s_cet, vcpu)) || + CC(is_noncanonical_msr_address(vmcs12->host_ssp, vcpu))) + return -EINVAL; + } else { + if (CC(vmcs12->host_s_cet >> 32) || CC(vmcs12->host_ssp >> 32)) + return -EINVAL; + } + } + return 0; } @@ -3162,6 +3258,9 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4))) return -EINVAL; + if (CC(vmcs12->guest_cr4 & X86_CR4_CET && !(vmcs12->guest_cr0 & X86_CR0_WP))) + return -EINVAL; + if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) || CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false)))) @@ -3211,6 +3310,23 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))) return -EINVAL; + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE) { + if (nested_vmx_check_cet_state_common(vcpu, vmcs12->guest_s_cet, + vmcs12->guest_ssp, + vmcs12->guest_ssp_tbl)) + return -EINVAL; + + /* + * Guest SSP must have 63:N bits identical, rather than + * be canonical (i.e., 63:N-1 bits identical), where N is + * the CPU's maximum linear-address width. Similar to + * is_noncanonical_msr_address(), use the host's + * linear-address width. + */ + if (CC(!__is_canonical_address(vmcs12->guest_ssp, max_host_virt_addr_bits() + 1))) + return -EINVAL; + } + if (nested_check_guest_non_reg_state(vmcs12)) return -EINVAL; @@ -3544,6 +3660,12 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) vmx->nested.pre_vmenter_bndcfgs = vmcs_read64(GUEST_BNDCFGS); + if (!vmx->nested.nested_run_pending || + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE)) + vmcs_read_cet_state(vcpu, &vmx->nested.pre_vmenter_s_cet, + &vmx->nested.pre_vmenter_ssp, + &vmx->nested.pre_vmenter_ssp_tbl); + /* * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and* * nested early checks are disabled. In the event of a "late" VM-Fail, @@ -4627,6 +4749,10 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER) vmcs12->guest_ia32_efer = vcpu->arch.efer; + + vmcs_read_cet_state(&vmx->vcpu, &vmcs12->guest_s_cet, + &vmcs12->guest_ssp, + &vmcs12->guest_ssp_tbl); } /* @@ -4752,6 +4878,18 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, if (vmcs12->vm_exit_controls & VM_EXIT_CLEAR_BNDCFGS) vmcs_write64(GUEST_BNDCFGS, 0); + /* + * Load CET state from host state if VM_EXIT_LOAD_CET_STATE is set. + * otherwise CET state should be retained across VM-exit, i.e., + * guest values should be propagated from vmcs12 to vmcs01. + */ + if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_CET_STATE) + vmcs_write_cet_state(vcpu, vmcs12->host_s_cet, vmcs12->host_ssp, + vmcs12->host_ssp_tbl); + else + vmcs_write_cet_state(vcpu, vmcs12->guest_s_cet, vmcs12->guest_ssp, + vmcs12->guest_ssp_tbl); + if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) { vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat); vcpu->arch.pat = vmcs12->host_ia32_pat; @@ -6570,14 +6708,17 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING); case EXIT_REASON_XSETBV: return true; - case EXIT_REASON_XSAVES: case EXIT_REASON_XRSTORS: + case EXIT_REASON_XSAVES: + case EXIT_REASON_XRSTORS: /* - * This should never happen, since it is not possible to - * set XSS to a non-zero value---neither in L1 nor in L2. - * If if it were, XSS would have to be checked against - * the XSS exit bitmap in vmcs12. + * Always forward XSAVES/XRSTORS to L1 as KVM doesn't utilize + * XSS-bitmap, and always loads vmcs02 with vmcs12's XSS-bitmap + * verbatim, i.e. any exit is due to L1's bitmap. WARN if + * XSAVES isn't enabled, as the CPU is supposed to inject #UD + * in that case, before consulting the XSS-bitmap. */ - return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_XSAVES); + WARN_ON_ONCE(!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_XSAVES)); + return true; case EXIT_REASON_UMWAIT: case EXIT_REASON_TPAUSE: return nested_cpu_has2(vmcs12, @@ -7038,13 +7179,17 @@ static void nested_vmx_setup_exit_ctls(struct vmcs_config *vmcs_conf, VM_EXIT_HOST_ADDR_SPACE_SIZE | #endif VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT | - VM_EXIT_CLEAR_BNDCFGS; + VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_CET_STATE; msrs->exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER | VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT | VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && + !kvm_cpu_cap_has(X86_FEATURE_IBT)) + msrs->exit_ctls_high &= ~VM_EXIT_LOAD_CET_STATE; + /* We support free control of debug control saving. */ msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS; } @@ -7060,11 +7205,16 @@ static void nested_vmx_setup_entry_ctls(struct vmcs_config *vmcs_conf, #ifdef CONFIG_X86_64 VM_ENTRY_IA32E_MODE | #endif - VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS; + VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS | + VM_ENTRY_LOAD_CET_STATE; msrs->entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER | VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL); + if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && + !kvm_cpu_cap_has(X86_FEATURE_IBT)) + msrs->entry_ctls_high &= ~VM_ENTRY_LOAD_CET_STATE; + /* We support free control of debug control loading. */ msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS; } @@ -7214,6 +7364,8 @@ static void nested_vmx_setup_basic(struct nested_vmx_msrs *msrs) msrs->basic |= VMX_BASIC_TRUE_CTLS; if (cpu_has_vmx_basic_inout()) msrs->basic |= VMX_BASIC_INOUT; + if (cpu_has_vmx_basic_no_hw_errcode_cc()) + msrs->basic |= VMX_BASIC_NO_HW_ERROR_CODE_CC; } static void nested_vmx_setup_cr_fixed(struct nested_vmx_msrs *msrs) diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 6eedcfc91070..983484d42ebf 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -309,6 +309,11 @@ static inline bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val) __kvm_is_valid_cr4(vcpu, val); } +static inline bool nested_cpu_has_no_hw_errcode_cc(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.msrs.basic & VMX_BASIC_NO_HW_ERROR_CODE_CC; +} + /* No difference in the restrictions on guest and host CR4 in VMX operation. */ #define nested_guest_cr4_valid nested_cr4_valid #define nested_host_cr4_valid nested_cr4_valid diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c index 106a72c923ca..4233b5ca9461 100644 --- a/arch/x86/kvm/vmx/vmcs12.c +++ b/arch/x86/kvm/vmx/vmcs12.c @@ -139,6 +139,9 @@ const unsigned short vmcs12_field_offsets[] = { FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions), FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp), FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip), + FIELD(GUEST_S_CET, guest_s_cet), + FIELD(GUEST_SSP, guest_ssp), + FIELD(GUEST_INTR_SSP_TABLE, guest_ssp_tbl), FIELD(HOST_CR0, host_cr0), FIELD(HOST_CR3, host_cr3), FIELD(HOST_CR4, host_cr4), @@ -151,5 +154,8 @@ const unsigned short vmcs12_field_offsets[] = { FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip), FIELD(HOST_RSP, host_rsp), FIELD(HOST_RIP, host_rip), + FIELD(HOST_S_CET, host_s_cet), + FIELD(HOST_SSP, host_ssp), + FIELD(HOST_INTR_SSP_TABLE, host_ssp_tbl), }; const unsigned int nr_vmcs12_fields = ARRAY_SIZE(vmcs12_field_offsets); diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h index 56fd150a6f24..4ad6b16525b9 100644 --- a/arch/x86/kvm/vmx/vmcs12.h +++ b/arch/x86/kvm/vmx/vmcs12.h @@ -117,7 +117,13 @@ struct __packed vmcs12 { natural_width host_ia32_sysenter_eip; natural_width host_rsp; natural_width host_rip; - natural_width paddingl[8]; /* room for future expansion */ + natural_width host_s_cet; + natural_width host_ssp; + natural_width host_ssp_tbl; + natural_width guest_s_cet; + natural_width guest_ssp; + natural_width guest_ssp_tbl; + natural_width paddingl[2]; /* room for future expansion */ u32 pin_based_vm_exec_control; u32 cpu_based_vm_exec_control; u32 exception_bitmap; @@ -294,6 +300,12 @@ static inline void vmx_check_vmcs12_offsets(void) CHECK_OFFSET(host_ia32_sysenter_eip, 656); CHECK_OFFSET(host_rsp, 664); CHECK_OFFSET(host_rip, 672); + CHECK_OFFSET(host_s_cet, 680); + CHECK_OFFSET(host_ssp, 688); + CHECK_OFFSET(host_ssp_tbl, 696); + CHECK_OFFSET(guest_s_cet, 704); + CHECK_OFFSET(guest_ssp, 712); + CHECK_OFFSET(guest_ssp_tbl, 720); CHECK_OFFSET(pin_based_vm_exec_control, 744); CHECK_OFFSET(cpu_based_vm_exec_control, 748); CHECK_OFFSET(exception_bitmap, 752); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 089d38c047a7..546272a5d34d 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2106,6 +2106,15 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) else msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; + case MSR_IA32_S_CET: + msr_info->data = vmcs_readl(GUEST_S_CET); + break; + case MSR_KVM_INTERNAL_GUEST_SSP: + msr_info->data = vmcs_readl(GUEST_SSP); + break; + case MSR_IA32_INT_SSP_TAB: + msr_info->data = vmcs_readl(GUEST_INTR_SSP_TABLE); + break; case MSR_IA32_DEBUGCTLMSR: msr_info->data = vmx_guest_debugctl_read(); break; @@ -2424,6 +2433,15 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) else vmx->pt_desc.guest.addr_a[index / 2] = data; break; + case MSR_IA32_S_CET: + vmcs_writel(GUEST_S_CET, data); + break; + case MSR_KVM_INTERNAL_GUEST_SSP: + vmcs_writel(GUEST_SSP, data); + break; + case MSR_IA32_INT_SSP_TAB: + vmcs_writel(GUEST_INTR_SSP_TABLE, data); + break; case MSR_IA32_PERF_CAPABILITIES: if (data & PERF_CAP_LBR_FMT) { if ((data & PERF_CAP_LBR_FMT) != @@ -2597,6 +2615,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, { VM_ENTRY_LOAD_IA32_EFER, VM_EXIT_LOAD_IA32_EFER }, { VM_ENTRY_LOAD_BNDCFGS, VM_EXIT_CLEAR_BNDCFGS }, { VM_ENTRY_LOAD_IA32_RTIT_CTL, VM_EXIT_CLEAR_IA32_RTIT_CTL }, + { VM_ENTRY_LOAD_CET_STATE, VM_EXIT_LOAD_CET_STATE }, }; memset(vmcs_conf, 0, sizeof(*vmcs_conf)); @@ -4083,6 +4102,8 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu) static void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu) { + bool intercept; + if (!cpu_has_vmx_msr_bitmap()) return; @@ -4128,6 +4149,23 @@ static void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu) vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W, !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); + if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) { + intercept = !guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK); + + vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL0_SSP, MSR_TYPE_RW, intercept); + vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL1_SSP, MSR_TYPE_RW, intercept); + vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL2_SSP, MSR_TYPE_RW, intercept); + vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL3_SSP, MSR_TYPE_RW, intercept); + } + + if (kvm_cpu_cap_has(X86_FEATURE_SHSTK) || kvm_cpu_cap_has(X86_FEATURE_IBT)) { + intercept = !guest_cpu_cap_has(vcpu, X86_FEATURE_IBT) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK); + + vmx_set_intercept_for_msr(vcpu, MSR_IA32_U_CET, MSR_TYPE_RW, intercept); + vmx_set_intercept_for_msr(vcpu, MSR_IA32_S_CET, MSR_TYPE_RW, intercept); + } + /* * x2APIC and LBR MSR intercepts are modified on-demand and cannot be * filtered by userspace. @@ -4288,6 +4326,21 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) if (cpu_has_load_ia32_efer()) vmcs_write64(HOST_IA32_EFER, kvm_host.efer); + + /* + * Supervisor shadow stack is not enabled on host side, i.e., + * host IA32_S_CET.SHSTK_EN bit is guaranteed to 0 now, per SDM + * description(RDSSP instruction), SSP is not readable in CPL0, + * so resetting the two registers to 0s at VM-Exit does no harm + * to kernel execution. When execution flow exits to userspace, + * SSP is reloaded from IA32_PL3_SSP. Check SDM Vol.2A/B Chapter + * 3 and 4 for details. + */ + if (cpu_has_load_cet_ctrl()) { + vmcs_writel(HOST_S_CET, kvm_host.s_cet); + vmcs_writel(HOST_SSP, 0); + vmcs_writel(HOST_INTR_SSP_TABLE, 0); + } } void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) @@ -4829,6 +4882,14 @@ void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ + if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) { + vmcs_writel(GUEST_SSP, 0); + vmcs_writel(GUEST_INTR_SSP_TABLE, 0); + } + if (kvm_cpu_cap_has(X86_FEATURE_IBT) || + kvm_cpu_cap_has(X86_FEATURE_SHSTK)) + vmcs_writel(GUEST_S_CET, 0); + kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); vpid_sync_context(vmx->vpid); @@ -6303,6 +6364,10 @@ void dump_vmcs(struct kvm_vcpu *vcpu) if (vmcs_read32(VM_EXIT_MSR_STORE_COUNT) > 0) vmx_dump_msrs("guest autostore", &vmx->msr_autostore.guest); + if (vmentry_ctl & VM_ENTRY_LOAD_CET_STATE) + pr_err("S_CET = 0x%016lx, SSP = 0x%016lx, SSP TABLE = 0x%016lx\n", + vmcs_readl(GUEST_S_CET), vmcs_readl(GUEST_SSP), + vmcs_readl(GUEST_INTR_SSP_TABLE)); pr_err("*** Host State ***\n"); pr_err("RIP = 0x%016lx RSP = 0x%016lx\n", vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP)); @@ -6333,6 +6398,10 @@ void dump_vmcs(struct kvm_vcpu *vcpu) vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL)); if (vmcs_read32(VM_EXIT_MSR_LOAD_COUNT) > 0) vmx_dump_msrs("host autoload", &vmx->msr_autoload.host); + if (vmexit_ctl & VM_EXIT_LOAD_CET_STATE) + pr_err("S_CET = 0x%016lx, SSP = 0x%016lx, SSP TABLE = 0x%016lx\n", + vmcs_readl(HOST_S_CET), vmcs_readl(HOST_SSP), + vmcs_readl(HOST_INTR_SSP_TABLE)); pr_err("*** Control State ***\n"); pr_err("CPUBased=0x%08x SecondaryExec=0x%08x TertiaryExec=0x%016llx\n", @@ -7686,6 +7755,8 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) cr4_fixed1_update(X86_CR4_PKE, ecx, feature_bit(PKU)); cr4_fixed1_update(X86_CR4_UMIP, ecx, feature_bit(UMIP)); cr4_fixed1_update(X86_CR4_LA57, ecx, feature_bit(LA57)); + cr4_fixed1_update(X86_CR4_CET, ecx, feature_bit(SHSTK)); + cr4_fixed1_update(X86_CR4_CET, edx, feature_bit(IBT)); entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 1); cr4_fixed1_update(X86_CR4_LAM_SUP, eax, feature_bit(LAM)); @@ -7914,7 +7985,6 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_UMIP); /* CPUID 0xD.1 */ - kvm_caps.supported_xss = 0; if (!cpu_has_vmx_xsaves()) kvm_cpu_cap_clear(X86_FEATURE_XSAVES); @@ -7926,6 +7996,18 @@ static __init void vmx_set_cpu_caps(void) if (cpu_has_vmx_waitpkg()) kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); + + /* + * Disable CET if unrestricted_guest is unsupported as KVM doesn't + * enforce CET HW behaviors in emulator. On platforms with + * VMX_BASIC[bit56] == 0, inject #CP at VMX entry with error code + * fails, so disable CET in this case too. + */ + if (!cpu_has_load_cet_ctrl() || !enable_unrestricted_guest || + !cpu_has_vmx_basic_no_hw_errcode_cc()) { + kvm_cpu_cap_clear(X86_FEATURE_SHSTK); + kvm_cpu_cap_clear(X86_FEATURE_IBT); + } } static bool vmx_is_io_intercepted(struct kvm_vcpu *vcpu, @@ -8404,6 +8486,14 @@ __init int vmx_hardware_setup(void) return -EOPNOTSUPP; } + /* + * Shadow paging doesn't have a (further) performance penalty + * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it + * by default + */ + if (!enable_ept) + allow_smaller_maxphyaddr = true; + if (!cpu_has_vmx_ept_ad_bits() || !enable_ept) enable_ept_ad_bits = 0; @@ -8529,6 +8619,13 @@ __init int vmx_hardware_setup(void) setup_default_sgx_lepubkeyhash(); + vmx_set_cpu_caps(); + + /* + * Configure nested capabilities after core CPU capabilities so that + * nested support can be conditional on base support, e.g. so that KVM + * can hide/show features based on kvm_cpu_cap_has(). + */ if (nested) { nested_vmx_setup_ctls_msrs(&vmcs_config, vmx_capability.ept); @@ -8537,8 +8634,6 @@ __init int vmx_hardware_setup(void) return r; } - vmx_set_cpu_caps(); - r = alloc_kvm_area(); if (r && nested) nested_vmx_hardware_unsetup(); @@ -8635,14 +8730,6 @@ int __init vmx_init(void) vmx_check_vmcs12_offsets(); - /* - * Shadow paging doesn't have a (further) performance penalty - * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it - * by default - */ - if (!enable_ept) - allow_smaller_maxphyaddr = true; - return 0; err_l1d_flush: diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 23d6e89b96f2..ea93121029f9 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -181,6 +181,9 @@ struct nested_vmx { */ u64 pre_vmenter_debugctl; u64 pre_vmenter_bndcfgs; + u64 pre_vmenter_s_cet; + u64 pre_vmenter_ssp; + u64 pre_vmenter_ssp_tbl; /* to migrate it to L1 if L2 writes to L1's CR8 directly */ int l1_tpr_threshold; @@ -484,7 +487,8 @@ static inline u8 vmx_get_rvi(void) VM_ENTRY_LOAD_IA32_EFER | \ VM_ENTRY_LOAD_BNDCFGS | \ VM_ENTRY_PT_CONCEAL_PIP | \ - VM_ENTRY_LOAD_IA32_RTIT_CTL) + VM_ENTRY_LOAD_IA32_RTIT_CTL | \ + VM_ENTRY_LOAD_CET_STATE) #define __KVM_REQUIRED_VMX_VM_EXIT_CONTROLS \ (VM_EXIT_SAVE_DEBUG_CONTROLS | \ @@ -506,7 +510,8 @@ static inline u8 vmx_get_rvi(void) VM_EXIT_LOAD_IA32_EFER | \ VM_EXIT_CLEAR_BNDCFGS | \ VM_EXIT_PT_CONCEAL_PIP | \ - VM_EXIT_CLEAR_IA32_RTIT_CTL) + VM_EXIT_CLEAR_IA32_RTIT_CTL | \ + VM_EXIT_LOAD_CET_STATE) #define KVM_REQUIRED_VMX_PIN_BASED_VM_EXEC_CONTROL \ (PIN_BASED_EXT_INTR_MASK | \ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c34981d28e9c..5542b8d83602 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -136,6 +136,9 @@ static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static DEFINE_MUTEX(vendor_module_lock); +static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); +static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); + struct kvm_x86_ops kvm_x86_ops __read_mostly; #define KVM_X86_OP(func) \ @@ -217,6 +220,15 @@ static struct kvm_user_return_msrs __percpu *user_return_msrs; | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \ | XFEATURE_MASK_PKRU | XFEATURE_MASK_XTILE) +#define XFEATURE_MASK_CET_ALL (XFEATURE_MASK_CET_USER | XFEATURE_MASK_CET_KERNEL) +/* + * Note, KVM supports exposing PT to the guest, but does not support context + * switching PT via XSTATE (KVM's PT virtualization relies on perf; swapping + * PT via guest XSTATE would clobber perf state), i.e. KVM doesn't support + * IA32_XSS[bit 8] (guests can/must use RDMSR/WRMSR to save/restore PT MSRs). + */ +#define KVM_SUPPORTED_XSS (XFEATURE_MASK_CET_ALL) + bool __read_mostly allow_smaller_maxphyaddr = 0; EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); @@ -332,7 +344,11 @@ static const u32 msrs_to_save_base[] = { MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, MSR_IA32_UMWAIT_CONTROL, - MSR_IA32_XFD, MSR_IA32_XFD_ERR, + MSR_IA32_XFD, MSR_IA32_XFD_ERR, MSR_IA32_XSS, + + MSR_IA32_U_CET, MSR_IA32_S_CET, + MSR_IA32_PL0_SSP, MSR_IA32_PL1_SSP, MSR_IA32_PL2_SSP, + MSR_IA32_PL3_SSP, MSR_IA32_INT_SSP_TAB, }; static const u32 msrs_to_save_pmu[] = { @@ -1171,6 +1187,9 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) (is_64_bit_mode(vcpu) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE))) return 1; + if (!(cr0 & X86_CR0_WP) && kvm_is_cr4_bit_set(vcpu, X86_CR4_CET)) + return 1; + kvm_x86_call(set_cr0)(vcpu, cr0); kvm_post_set_cr0(vcpu, old_cr0, cr0); @@ -1371,6 +1390,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; } + if ((cr4 & X86_CR4_CET) && !kvm_is_cr0_bit_set(vcpu, X86_CR0_WP)) + return 1; + kvm_x86_call(set_cr4)(vcpu, cr4); kvm_post_set_cr4(vcpu, old_cr4, cr4); @@ -1875,6 +1897,44 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, data = (u32)data; break; + case MSR_IA32_U_CET: + case MSR_IA32_S_CET: + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_IBT)) + return KVM_MSR_RET_UNSUPPORTED; + if (!kvm_is_valid_u_s_cet(vcpu, data)) + return 1; + break; + case MSR_KVM_INTERNAL_GUEST_SSP: + if (!host_initiated) + return 1; + fallthrough; + /* + * Note that the MSR emulation here is flawed when a vCPU + * doesn't support the Intel 64 architecture. The expected + * architectural behavior in this case is that the upper 32 + * bits do not exist and should always read '0'. However, + * because the actual hardware on which the virtual CPU is + * running does support Intel 64, XRSTORS/XSAVES in the + * guest could observe behavior that violates the + * architecture. Intercepting XRSTORS/XSAVES for this + * special case isn't deemed worthwhile. + */ + case MSR_IA32_PL0_SSP ... MSR_IA32_INT_SSP_TAB: + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) + return KVM_MSR_RET_UNSUPPORTED; + /* + * MSR_IA32_INT_SSP_TAB is not present on processors that do + * not support Intel 64 architecture. + */ + if (index == MSR_IA32_INT_SSP_TAB && !guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) + return KVM_MSR_RET_UNSUPPORTED; + if (is_noncanonical_msr_address(data, vcpu)) + return 1; + /* All SSP MSRs except MSR_IA32_INT_SSP_TAB must be 4-byte aligned */ + if (index != MSR_IA32_INT_SSP_TAB && !IS_ALIGNED(data, 4)) + return 1; + break; } msr.data = data; @@ -1919,6 +1979,20 @@ static int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID)) return 1; break; + case MSR_IA32_U_CET: + case MSR_IA32_S_CET: + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_IBT)) + return KVM_MSR_RET_UNSUPPORTED; + break; + case MSR_KVM_INTERNAL_GUEST_SSP: + if (!host_initiated) + return 1; + fallthrough; + case MSR_IA32_PL0_SSP ... MSR_IA32_INT_SSP_TAB: + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) + return KVM_MSR_RET_UNSUPPORTED; + break; } msr.index = index; @@ -3799,6 +3873,67 @@ static void record_steal_time(struct kvm_vcpu *vcpu) mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } +/* + * Returns true if the MSR in question is managed via XSTATE, i.e. is context + * switched with the rest of guest FPU state. Note! S_CET is _not_ context + * switched via XSTATE even though it _is_ saved/restored via XSAVES/XRSTORS. + * Because S_CET is loaded on VM-Enter and VM-Exit via dedicated VMCS fields, + * the value saved/restored via XSTATE is always the host's value. That detail + * is _extremely_ important, as the guest's S_CET must _never_ be resident in + * hardware while executing in the host. Loading guest values for U_CET and + * PL[0-3]_SSP while executing in the kernel is safe, as U_CET is specific to + * userspace, and PL[0-3]_SSP are only consumed when transitioning to lower + * privilege levels, i.e. are effectively only consumed by userspace as well. + */ +static bool is_xstate_managed_msr(struct kvm_vcpu *vcpu, u32 msr) +{ + if (!vcpu) + return false; + + switch (msr) { + case MSR_IA32_U_CET: + return guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) || + guest_cpu_cap_has(vcpu, X86_FEATURE_IBT); + case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP: + return guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK); + default: + return false; + } +} + +/* + * Lock (and if necessary, re-load) the guest FPU, i.e. XSTATE, and access an + * MSR that is managed via XSTATE. Note, the caller is responsible for doing + * the initial FPU load, this helper only ensures that guest state is resident + * in hardware (the kernel can load its FPU state in IRQ context). + */ +static __always_inline void kvm_access_xstate_msr(struct kvm_vcpu *vcpu, + struct msr_data *msr_info, + int access) +{ + BUILD_BUG_ON(access != MSR_TYPE_R && access != MSR_TYPE_W); + + KVM_BUG_ON(!is_xstate_managed_msr(vcpu, msr_info->index), vcpu->kvm); + KVM_BUG_ON(!vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm); + + kvm_fpu_get(); + if (access == MSR_TYPE_R) + rdmsrq(msr_info->index, msr_info->data); + else + wrmsrq(msr_info->index, msr_info->data); + kvm_fpu_put(); +} + +static void kvm_set_xstate_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + kvm_access_xstate_msr(vcpu, msr_info, MSR_TYPE_W); +} + +static void kvm_get_xstate_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + kvm_access_xstate_msr(vcpu, msr_info, MSR_TYPE_R); +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u32 msr = msr_info->index; @@ -3990,16 +4125,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } break; case MSR_IA32_XSS: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) - return 1; - /* - * KVM supports exposing PT to the guest, but does not support - * IA32_XSS[bit 8]. Guests have to use RDMSR/WRMSR rather than - * XSAVES/XRSTORS to save/restore PT MSRs. - */ - if (data & ~kvm_caps.supported_xss) + if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + return KVM_MSR_RET_UNSUPPORTED; + + if (data & ~vcpu->arch.guest_supported_xss) return 1; + if (vcpu->arch.ia32_xss == data) + break; vcpu->arch.ia32_xss = data; vcpu->arch.cpuid_dynamic_bits_dirty = true; break; @@ -4183,6 +4315,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.guest_fpu.xfd_err = data; break; #endif + case MSR_IA32_U_CET: + case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP: + kvm_set_xstate_msr(vcpu, msr_info); + break; default: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); @@ -4532,6 +4668,10 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.guest_fpu.xfd_err; break; #endif + case MSR_IA32_U_CET: + case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP: + kvm_get_xstate_msr(vcpu, msr_info); + break; default: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); @@ -4552,11 +4692,25 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, int (*do_msr)(struct kvm_vcpu *vcpu, unsigned index, u64 *data)) { + bool fpu_loaded = false; int i; - for (i = 0; i < msrs->nmsrs; ++i) + for (i = 0; i < msrs->nmsrs; ++i) { + /* + * If userspace is accessing one or more XSTATE-managed MSRs, + * temporarily load the guest's FPU state so that the guest's + * MSR value(s) is resident in hardware and thus can be accessed + * via RDMSR/WRMSR. + */ + if (!fpu_loaded && is_xstate_managed_msr(vcpu, entries[i].index)) { + kvm_load_guest_fpu(vcpu); + fpu_loaded = true; + } if (do_msr(vcpu, entries[i].index, &entries[i].data)) break; + } + if (fpu_loaded) + kvm_put_guest_fpu(vcpu); return i; } @@ -4741,6 +4895,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_IRQFD_RESAMPLE: case KVM_CAP_MEMORY_FAULT_INFO: case KVM_CAP_X86_GUEST_MODE: + case KVM_CAP_ONE_REG: r = 1; break; case KVM_CAP_PRE_FAULT_MEMORY: @@ -5919,6 +6074,134 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, } } +struct kvm_x86_reg_id { + __u32 index; + __u8 type; + __u8 rsvd1; + __u8 rsvd2:4; + __u8 size:4; + __u8 x86; +}; + +static int kvm_translate_kvm_reg(struct kvm_vcpu *vcpu, + struct kvm_x86_reg_id *reg) +{ + switch (reg->index) { + case KVM_REG_GUEST_SSP: + /* + * FIXME: If host-initiated accesses are ever exempted from + * ignore_msrs (in kvm_do_msr_access()), drop this manual check + * and rely on KVM's standard checks to reject accesses to regs + * that don't exist. + */ + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) + return -EINVAL; + + reg->type = KVM_X86_REG_TYPE_MSR; + reg->index = MSR_KVM_INTERNAL_GUEST_SSP; + break; + default: + return -EINVAL; + } + return 0; +} + +static int kvm_get_one_msr(struct kvm_vcpu *vcpu, u32 msr, u64 __user *user_val) +{ + u64 val; + + if (do_get_msr(vcpu, msr, &val)) + return -EINVAL; + + if (put_user(val, user_val)) + return -EFAULT; + + return 0; +} + +static int kvm_set_one_msr(struct kvm_vcpu *vcpu, u32 msr, u64 __user *user_val) +{ + u64 val; + + if (get_user(val, user_val)) + return -EFAULT; + + if (do_set_msr(vcpu, msr, &val)) + return -EINVAL; + + return 0; +} + +static int kvm_get_set_one_reg(struct kvm_vcpu *vcpu, unsigned int ioctl, + void __user *argp) +{ + struct kvm_one_reg one_reg; + struct kvm_x86_reg_id *reg; + u64 __user *user_val; + bool load_fpu; + int r; + + if (copy_from_user(&one_reg, argp, sizeof(one_reg))) + return -EFAULT; + + if ((one_reg.id & KVM_REG_ARCH_MASK) != KVM_REG_X86) + return -EINVAL; + + reg = (struct kvm_x86_reg_id *)&one_reg.id; + if (reg->rsvd1 || reg->rsvd2) + return -EINVAL; + + if (reg->type == KVM_X86_REG_TYPE_KVM) { + r = kvm_translate_kvm_reg(vcpu, reg); + if (r) + return r; + } + + if (reg->type != KVM_X86_REG_TYPE_MSR) + return -EINVAL; + + if ((one_reg.id & KVM_REG_SIZE_MASK) != KVM_REG_SIZE_U64) + return -EINVAL; + + guard(srcu)(&vcpu->kvm->srcu); + + load_fpu = is_xstate_managed_msr(vcpu, reg->index); + if (load_fpu) + kvm_load_guest_fpu(vcpu); + + user_val = u64_to_user_ptr(one_reg.addr); + if (ioctl == KVM_GET_ONE_REG) + r = kvm_get_one_msr(vcpu, reg->index, user_val); + else + r = kvm_set_one_msr(vcpu, reg->index, user_val); + + if (load_fpu) + kvm_put_guest_fpu(vcpu); + return r; +} + +static int kvm_get_reg_list(struct kvm_vcpu *vcpu, + struct kvm_reg_list __user *user_list) +{ + u64 nr_regs = guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) ? 1 : 0; + u64 user_nr_regs; + + if (get_user(user_nr_regs, &user_list->n)) + return -EFAULT; + + if (put_user(nr_regs, &user_list->n)) + return -EFAULT; + + if (user_nr_regs < nr_regs) + return -E2BIG; + + if (nr_regs && + put_user(KVM_X86_REG_KVM(KVM_REG_GUEST_SSP), &user_list->reg[0])) + return -EFAULT; + + return 0; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -6035,6 +6318,13 @@ long kvm_arch_vcpu_ioctl(struct file *filp, srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } + case KVM_GET_ONE_REG: + case KVM_SET_ONE_REG: + r = kvm_get_set_one_reg(vcpu, ioctl, argp); + break; + case KVM_GET_REG_LIST: + r = kvm_get_reg_list(vcpu, argp); + break; case KVM_TPR_ACCESS_REPORTING: { struct kvm_tpr_access_ctl tac; @@ -7409,6 +7699,24 @@ static void kvm_probe_msr_to_save(u32 msr_index) if (!(kvm_get_arch_capabilities() & ARCH_CAP_TSX_CTRL_MSR)) return; break; + case MSR_IA32_XSS: + if (!kvm_caps.supported_xss) + return; + break; + case MSR_IA32_U_CET: + case MSR_IA32_S_CET: + if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && + !kvm_cpu_cap_has(X86_FEATURE_IBT)) + return; + break; + case MSR_IA32_INT_SSP_TAB: + if (!kvm_cpu_cap_has(X86_FEATURE_LM)) + return; + fallthrough; + case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP: + if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK)) + return; + break; default: break; } @@ -8440,6 +8748,15 @@ static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt, static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata) { + /* + * Treat emulator accesses to the current shadow stack pointer as host- + * initiated, as they aren't true MSR accesses (SSP is a "just a reg"), + * and this API is used only for implicit accesses, i.e. not RDMSR, and + * so the index is fully KVM-controlled. + */ + if (unlikely(msr_index == MSR_KVM_INTERNAL_GUEST_SSP)) + return kvm_msr_read(emul_to_vcpu(ctxt), msr_index, pdata); + return __kvm_emulate_msr_read(emul_to_vcpu(ctxt), msr_index, pdata); } @@ -9696,6 +10013,18 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) return -EIO; } + if (boot_cpu_has(X86_FEATURE_SHSTK) || boot_cpu_has(X86_FEATURE_IBT)) { + rdmsrq(MSR_IA32_S_CET, kvm_host.s_cet); + /* + * Linux doesn't yet support supervisor shadow stacks (SSS), so + * KVM doesn't save/restore the associated MSRs, i.e. KVM may + * clobber the host values. Yell and refuse to load if SSS is + * unexpectedly enabled, e.g. to avoid crashing the host. + */ + if (WARN_ON_ONCE(kvm_host.s_cet & CET_SHSTK_EN)) + return -EIO; + } + memset(&kvm_caps, 0, sizeof(kvm_caps)); x86_emulator_cache = kvm_alloc_emulator_cache(); @@ -9723,14 +10052,17 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) kvm_host.xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); kvm_caps.supported_xcr0 = kvm_host.xcr0 & KVM_SUPPORTED_XCR0; } + + if (boot_cpu_has(X86_FEATURE_XSAVES)) { + rdmsrq(MSR_IA32_XSS, kvm_host.xss); + kvm_caps.supported_xss = kvm_host.xss & KVM_SUPPORTED_XSS; + } + kvm_caps.supported_quirks = KVM_X86_VALID_QUIRKS; kvm_caps.inapplicable_quirks = KVM_X86_CONDITIONAL_QUIRKS; rdmsrq_safe(MSR_EFER, &kvm_host.efer); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - rdmsrq(MSR_IA32_XSS, kvm_host.xss); - kvm_init_pmu_capability(ops->pmu_ops); if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) @@ -9779,6 +10111,16 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) kvm_caps.supported_xss = 0; + if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && + !kvm_cpu_cap_has(X86_FEATURE_IBT)) + kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; + + if ((kvm_caps.supported_xss & XFEATURE_MASK_CET_ALL) != XFEATURE_MASK_CET_ALL) { + kvm_cpu_cap_clear(X86_FEATURE_SHSTK); + kvm_cpu_cap_clear(X86_FEATURE_IBT); + kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; + } + if (kvm_caps.has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that @@ -11871,6 +12213,25 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int ret; + if (kvm_is_cr4_bit_set(vcpu, X86_CR4_CET)) { + u64 u_cet, s_cet; + + /* + * Check both User and Supervisor on task switches as inter- + * privilege level task switches are impacted by CET at both + * the current privilege level and the new privilege level, and + * that information is not known at this time. The expectation + * is that the guest won't require emulation of task switches + * while using IBT or Shadow Stacks. + */ + if (__kvm_emulate_msr_read(vcpu, MSR_IA32_U_CET, &u_cet) || + __kvm_emulate_msr_read(vcpu, MSR_IA32_S_CET, &s_cet)) + goto unhandled_task_switch; + + if ((u_cet | s_cet) & (CET_ENDBR_EN | CET_SHSTK_EN)) + goto unhandled_task_switch; + } + init_emulate_ctxt(vcpu); ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason, @@ -11880,17 +12241,19 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, * Report an error userspace if MMIO is needed, as KVM doesn't support * MMIO during a task switch (or any other complex operation). */ - if (ret || vcpu->mmio_needed) { - vcpu->mmio_needed = false; - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; - return 0; - } + if (ret || vcpu->mmio_needed) + goto unhandled_task_switch; kvm_rip_write(vcpu, ctxt->eip); kvm_set_rflags(vcpu, ctxt->eflags); return 1; + +unhandled_task_switch: + vcpu->mmio_needed = false; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return 0; } EXPORT_SYMBOL_GPL(kvm_task_switch); @@ -12438,10 +12801,11 @@ static void kvm_xstate_reset(struct kvm_vcpu *vcpu, bool init_event) /* * On INIT, only select XSTATE components are zeroed, most components * are unchanged. Currently, the only components that are zeroed and - * supported by KVM are MPX related. + * supported by KVM are MPX and CET related. */ xfeatures_mask = (kvm_caps.supported_xcr0 | kvm_caps.supported_xss) & - (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); + (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR | + XFEATURE_MASK_CET_ALL); if (!xfeatures_mask) return; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 786e36fcd0fb..f3dc77f006f9 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -50,6 +50,7 @@ struct kvm_host_values { u64 efer; u64 xcr0; u64 xss; + u64 s_cet; u64 arch_capabilities; }; @@ -101,6 +102,16 @@ do { \ #define KVM_SVM_DEFAULT_PLE_WINDOW_MAX USHRT_MAX #define KVM_SVM_DEFAULT_PLE_WINDOW 3000 +/* + * KVM's internal, non-ABI indices for synthetic MSRs. The values themselves + * are arbitrary and have no meaning, the only requirement is that they don't + * conflict with "real" MSRs that KVM supports. Use values at the upper end + * of KVM's reserved paravirtual MSR range to minimize churn, i.e. these values + * will be usable until KVM exhausts its supply of paravirtual MSR indices. + */ + +#define MSR_KVM_INTERNAL_GUEST_SSP 0x4b564dff + static inline unsigned int __grow_ple_window(unsigned int val, unsigned int base, unsigned int modifier, unsigned int max) { @@ -669,6 +680,9 @@ static inline bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) __reserved_bits |= X86_CR4_PCIDE; \ if (!__cpu_has(__c, X86_FEATURE_LAM)) \ __reserved_bits |= X86_CR4_LAM_SUP; \ + if (!__cpu_has(__c, X86_FEATURE_SHSTK) && \ + !__cpu_has(__c, X86_FEATURE_IBT)) \ + __reserved_bits |= X86_CR4_CET; \ __reserved_bits; \ }) @@ -700,4 +714,27 @@ int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, int cpl, int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); +#define CET_US_RESERVED_BITS GENMASK(9, 6) +#define CET_US_SHSTK_MASK_BITS GENMASK(1, 0) +#define CET_US_IBT_MASK_BITS (GENMASK_ULL(5, 2) | GENMASK_ULL(63, 10)) +#define CET_US_LEGACY_BITMAP_BASE(data) ((data) >> 12) + +static inline bool kvm_is_valid_u_s_cet(struct kvm_vcpu *vcpu, u64 data) +{ + if (data & CET_US_RESERVED_BITS) + return false; + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) && + (data & CET_US_SHSTK_MASK_BITS)) + return false; + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_IBT) && + (data & CET_US_IBT_MASK_BITS)) + return false; + if (!IS_ALIGNED(CET_US_LEGACY_BITMAP_BASE(data), 4)) + return false; + /* IBT can be suppressed iff the TRACKER isn't WAIT_ENDBR. */ + if ((data & CET_SUPPRESS) && (data & CET_WAIT_ENDBR)) + return false; + + return true; +} #endif diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 8926ff6808cf..148d427ff24b 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -87,6 +87,7 @@ TEST_GEN_PROGS_x86 += x86/kvm_clock_test TEST_GEN_PROGS_x86 += x86/kvm_pv_test TEST_GEN_PROGS_x86 += x86/kvm_buslock_test TEST_GEN_PROGS_x86 += x86/monitor_mwait_test +TEST_GEN_PROGS_x86 += x86/msrs_test TEST_GEN_PROGS_x86 += x86/nested_emulation_test TEST_GEN_PROGS_x86 += x86/nested_exceptions_test TEST_GEN_PROGS_x86 += x86/platform_info_test diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index fbe875eafca5..51cd84b9ca66 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -1362,6 +1362,11 @@ static inline bool kvm_is_unrestricted_guest_enabled(void) return get_kvm_intel_param_bool("unrestricted_guest"); } +static inline bool kvm_is_ignore_msrs(void) +{ + return get_kvm_param_bool("ignore_msrs"); +} + uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, int *level); uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr); diff --git a/tools/testing/selftests/kvm/x86/msrs_test.c b/tools/testing/selftests/kvm/x86/msrs_test.c new file mode 100644 index 000000000000..40d918aedce6 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/msrs_test.c @@ -0,0 +1,489 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <asm/msr-index.h> + +#include <stdint.h> + +#include "kvm_util.h" +#include "processor.h" + +/* Use HYPERVISOR for MSRs that are emulated unconditionally (as is HYPERVISOR). */ +#define X86_FEATURE_NONE X86_FEATURE_HYPERVISOR + +struct kvm_msr { + const struct kvm_x86_cpu_feature feature; + const struct kvm_x86_cpu_feature feature2; + const char *name; + const u64 reset_val; + const u64 write_val; + const u64 rsvd_val; + const u32 index; + const bool is_kvm_defined; +}; + +#define ____MSR_TEST(msr, str, val, rsvd, reset, feat, f2, is_kvm) \ +{ \ + .index = msr, \ + .name = str, \ + .write_val = val, \ + .rsvd_val = rsvd, \ + .reset_val = reset, \ + .feature = X86_FEATURE_ ##feat, \ + .feature2 = X86_FEATURE_ ##f2, \ + .is_kvm_defined = is_kvm, \ +} + +#define __MSR_TEST(msr, str, val, rsvd, reset, feat) \ + ____MSR_TEST(msr, str, val, rsvd, reset, feat, feat, false) + +#define MSR_TEST_NON_ZERO(msr, val, rsvd, reset, feat) \ + __MSR_TEST(msr, #msr, val, rsvd, reset, feat) + +#define MSR_TEST(msr, val, rsvd, feat) \ + __MSR_TEST(msr, #msr, val, rsvd, 0, feat) + +#define MSR_TEST2(msr, val, rsvd, feat, f2) \ + ____MSR_TEST(msr, #msr, val, rsvd, 0, feat, f2, false) + +/* + * Note, use a page aligned value for the canonical value so that the value + * is compatible with MSRs that use bits 11:0 for things other than addresses. + */ +static const u64 canonical_val = 0x123456789000ull; + +/* + * Arbitrary value with bits set in every byte, but not all bits set. This is + * also a non-canonical value, but that's coincidental (any 64-bit value with + * an alternating 0s/1s pattern will be non-canonical). + */ +static const u64 u64_val = 0xaaaa5555aaaa5555ull; + +#define MSR_TEST_CANONICAL(msr, feat) \ + __MSR_TEST(msr, #msr, canonical_val, NONCANONICAL, 0, feat) + +#define MSR_TEST_KVM(msr, val, rsvd, feat) \ + ____MSR_TEST(KVM_REG_ ##msr, #msr, val, rsvd, 0, feat, feat, true) + +/* + * The main struct must be scoped to a function due to the use of structures to + * define features. For the global structure, allocate enough space for the + * foreseeable future without getting too ridiculous, to minimize maintenance + * costs (bumping the array size every time an MSR is added is really annoying). + */ +static struct kvm_msr msrs[128]; +static int idx; + +static bool ignore_unsupported_msrs; + +static u64 fixup_rdmsr_val(u32 msr, u64 want) +{ + /* + * AMD CPUs drop bits 63:32 on some MSRs that Intel CPUs support. KVM + * is supposed to emulate that behavior based on guest vendor model + * (which is the same as the host vendor model for this test). + */ + if (!host_cpu_is_amd) + return want; + + switch (msr) { + case MSR_IA32_SYSENTER_ESP: + case MSR_IA32_SYSENTER_EIP: + case MSR_TSC_AUX: + return want & GENMASK_ULL(31, 0); + default: + return want; + } +} + +static void __rdmsr(u32 msr, u64 want) +{ + u64 val; + u8 vec; + + vec = rdmsr_safe(msr, &val); + __GUEST_ASSERT(!vec, "Unexpected %s on RDMSR(0x%x)", ex_str(vec), msr); + + __GUEST_ASSERT(val == want, "Wanted 0x%lx from RDMSR(0x%x), got 0x%lx", + want, msr, val); +} + +static void __wrmsr(u32 msr, u64 val) +{ + u8 vec; + + vec = wrmsr_safe(msr, val); + __GUEST_ASSERT(!vec, "Unexpected %s on WRMSR(0x%x, 0x%lx)", + ex_str(vec), msr, val); + __rdmsr(msr, fixup_rdmsr_val(msr, val)); +} + +static void guest_test_supported_msr(const struct kvm_msr *msr) +{ + __rdmsr(msr->index, msr->reset_val); + __wrmsr(msr->index, msr->write_val); + GUEST_SYNC(fixup_rdmsr_val(msr->index, msr->write_val)); + + __rdmsr(msr->index, msr->reset_val); +} + +static void guest_test_unsupported_msr(const struct kvm_msr *msr) +{ + u64 val; + u8 vec; + + /* + * KVM's ABI with respect to ignore_msrs is a mess and largely beyond + * repair, just skip the unsupported MSR tests. + */ + if (ignore_unsupported_msrs) + goto skip_wrmsr_gp; + + /* + * {S,U}_CET exist if IBT or SHSTK is supported, but with bits that are + * writable only if their associated feature is supported. Skip the + * RDMSR #GP test if the secondary feature is supported, but perform + * the WRMSR #GP test as the to-be-written value is tied to the primary + * feature. For all other MSRs, simply do nothing. + */ + if (this_cpu_has(msr->feature2)) { + if (msr->index != MSR_IA32_U_CET && + msr->index != MSR_IA32_S_CET) + goto skip_wrmsr_gp; + + goto skip_rdmsr_gp; + } + + vec = rdmsr_safe(msr->index, &val); + __GUEST_ASSERT(vec == GP_VECTOR, "Wanted #GP on RDMSR(0x%x), got %s", + msr->index, ex_str(vec)); + +skip_rdmsr_gp: + vec = wrmsr_safe(msr->index, msr->write_val); + __GUEST_ASSERT(vec == GP_VECTOR, "Wanted #GP on WRMSR(0x%x, 0x%lx), got %s", + msr->index, msr->write_val, ex_str(vec)); + +skip_wrmsr_gp: + GUEST_SYNC(0); +} + +void guest_test_reserved_val(const struct kvm_msr *msr) +{ + /* Skip reserved value checks as well, ignore_msrs is trully a mess. */ + if (ignore_unsupported_msrs) + return; + + /* + * If the CPU will truncate the written value (e.g. SYSENTER on AMD), + * expect success and a truncated value, not #GP. + */ + if (!this_cpu_has(msr->feature) || + msr->rsvd_val == fixup_rdmsr_val(msr->index, msr->rsvd_val)) { + u8 vec = wrmsr_safe(msr->index, msr->rsvd_val); + + __GUEST_ASSERT(vec == GP_VECTOR, + "Wanted #GP on WRMSR(0x%x, 0x%lx), got %s", + msr->index, msr->rsvd_val, ex_str(vec)); + } else { + __wrmsr(msr->index, msr->rsvd_val); + __wrmsr(msr->index, msr->reset_val); + } +} + +static void guest_main(void) +{ + for (;;) { + const struct kvm_msr *msr = &msrs[READ_ONCE(idx)]; + + if (this_cpu_has(msr->feature)) + guest_test_supported_msr(msr); + else + guest_test_unsupported_msr(msr); + + if (msr->rsvd_val) + guest_test_reserved_val(msr); + + GUEST_SYNC(msr->reset_val); + } +} + +static bool has_one_reg; +static bool use_one_reg; + +#define KVM_X86_MAX_NR_REGS 1 + +static bool vcpu_has_reg(struct kvm_vcpu *vcpu, u64 reg) +{ + struct { + struct kvm_reg_list list; + u64 regs[KVM_X86_MAX_NR_REGS]; + } regs = {}; + int r, i; + + /* + * If KVM_GET_REG_LIST succeeds with n=0, i.e. there are no supported + * regs, then the vCPU obviously doesn't support the reg. + */ + r = __vcpu_ioctl(vcpu, KVM_GET_REG_LIST, ®s.list); + if (!r) + return false; + + TEST_ASSERT_EQ(errno, E2BIG); + + /* + * KVM x86 is expected to support enumerating a relative small number + * of regs. The majority of registers supported by KVM_{G,S}ET_ONE_REG + * are enumerated via other ioctls, e.g. KVM_GET_MSR_INDEX_LIST. For + * simplicity, hardcode the maximum number of regs and manually update + * the test as necessary. + */ + TEST_ASSERT(regs.list.n <= KVM_X86_MAX_NR_REGS, + "KVM reports %llu regs, test expects at most %u regs, stale test?", + regs.list.n, KVM_X86_MAX_NR_REGS); + + vcpu_ioctl(vcpu, KVM_GET_REG_LIST, ®s.list); + for (i = 0; i < regs.list.n; i++) { + if (regs.regs[i] == reg) + return true; + } + + return false; +} + +static void host_test_kvm_reg(struct kvm_vcpu *vcpu) +{ + bool has_reg = vcpu_cpuid_has(vcpu, msrs[idx].feature); + u64 reset_val = msrs[idx].reset_val; + u64 write_val = msrs[idx].write_val; + u64 rsvd_val = msrs[idx].rsvd_val; + u32 reg = msrs[idx].index; + u64 val; + int r; + + if (!use_one_reg) + return; + + TEST_ASSERT_EQ(vcpu_has_reg(vcpu, KVM_X86_REG_KVM(reg)), has_reg); + + if (!has_reg) { + r = __vcpu_get_reg(vcpu, KVM_X86_REG_KVM(reg), &val); + TEST_ASSERT(r && errno == EINVAL, + "Expected failure on get_reg(0x%x)", reg); + rsvd_val = 0; + goto out; + } + + val = vcpu_get_reg(vcpu, KVM_X86_REG_KVM(reg)); + TEST_ASSERT(val == reset_val, "Wanted 0x%lx from get_reg(0x%x), got 0x%lx", + reset_val, reg, val); + + vcpu_set_reg(vcpu, KVM_X86_REG_KVM(reg), write_val); + val = vcpu_get_reg(vcpu, KVM_X86_REG_KVM(reg)); + TEST_ASSERT(val == write_val, "Wanted 0x%lx from get_reg(0x%x), got 0x%lx", + write_val, reg, val); + +out: + r = __vcpu_set_reg(vcpu, KVM_X86_REG_KVM(reg), rsvd_val); + TEST_ASSERT(r, "Expected failure on set_reg(0x%x, 0x%lx)", reg, rsvd_val); +} + +static void host_test_msr(struct kvm_vcpu *vcpu, u64 guest_val) +{ + u64 reset_val = msrs[idx].reset_val; + u32 msr = msrs[idx].index; + u64 val; + + if (!kvm_cpu_has(msrs[idx].feature)) + return; + + val = vcpu_get_msr(vcpu, msr); + TEST_ASSERT(val == guest_val, "Wanted 0x%lx from get_msr(0x%x), got 0x%lx", + guest_val, msr, val); + + if (use_one_reg) + vcpu_set_reg(vcpu, KVM_X86_REG_MSR(msr), reset_val); + else + vcpu_set_msr(vcpu, msr, reset_val); + + val = vcpu_get_msr(vcpu, msr); + TEST_ASSERT(val == reset_val, "Wanted 0x%lx from get_msr(0x%x), got 0x%lx", + reset_val, msr, val); + + if (!has_one_reg) + return; + + val = vcpu_get_reg(vcpu, KVM_X86_REG_MSR(msr)); + TEST_ASSERT(val == reset_val, "Wanted 0x%lx from get_reg(0x%x), got 0x%lx", + reset_val, msr, val); +} + +static void do_vcpu_run(struct kvm_vcpu *vcpu) +{ + struct ucall uc; + + for (;;) { + vcpu_run(vcpu); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + host_test_msr(vcpu, uc.args[1]); + return; + case UCALL_PRINTF: + pr_info("%s", uc.buffer); + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + case UCALL_DONE: + TEST_FAIL("Unexpected UCALL_DONE"); + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } + } +} + +static void vcpus_run(struct kvm_vcpu **vcpus, const int NR_VCPUS) +{ + int i; + + for (i = 0; i < NR_VCPUS; i++) + do_vcpu_run(vcpus[i]); +} + +#define MISC_ENABLES_RESET_VAL (MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL | MSR_IA32_MISC_ENABLE_BTS_UNAVAIL) + +static void test_msrs(void) +{ + const struct kvm_msr __msrs[] = { + MSR_TEST_NON_ZERO(MSR_IA32_MISC_ENABLE, + MISC_ENABLES_RESET_VAL | MSR_IA32_MISC_ENABLE_FAST_STRING, + MSR_IA32_MISC_ENABLE_FAST_STRING, MISC_ENABLES_RESET_VAL, NONE), + MSR_TEST_NON_ZERO(MSR_IA32_CR_PAT, 0x07070707, 0, 0x7040600070406, NONE), + + /* + * TSC_AUX is supported if RDTSCP *or* RDPID is supported. Add + * entries for each features so that TSC_AUX doesn't exists for + * the "unsupported" vCPU, and obviously to test both cases. + */ + MSR_TEST2(MSR_TSC_AUX, 0x12345678, u64_val, RDTSCP, RDPID), + MSR_TEST2(MSR_TSC_AUX, 0x12345678, u64_val, RDPID, RDTSCP), + + MSR_TEST(MSR_IA32_SYSENTER_CS, 0x1234, 0, NONE), + /* + * SYSENTER_{ESP,EIP} are technically non-canonical on Intel, + * but KVM doesn't emulate that behavior on emulated writes, + * i.e. this test will observe different behavior if the MSR + * writes are handed by hardware vs. KVM. KVM's behavior is + * intended (though far from ideal), so don't bother testing + * non-canonical values. + */ + MSR_TEST(MSR_IA32_SYSENTER_ESP, canonical_val, 0, NONE), + MSR_TEST(MSR_IA32_SYSENTER_EIP, canonical_val, 0, NONE), + + MSR_TEST_CANONICAL(MSR_FS_BASE, LM), + MSR_TEST_CANONICAL(MSR_GS_BASE, LM), + MSR_TEST_CANONICAL(MSR_KERNEL_GS_BASE, LM), + MSR_TEST_CANONICAL(MSR_LSTAR, LM), + MSR_TEST_CANONICAL(MSR_CSTAR, LM), + MSR_TEST(MSR_SYSCALL_MASK, 0xffffffff, 0, LM), + + MSR_TEST2(MSR_IA32_S_CET, CET_SHSTK_EN, CET_RESERVED, SHSTK, IBT), + MSR_TEST2(MSR_IA32_S_CET, CET_ENDBR_EN, CET_RESERVED, IBT, SHSTK), + MSR_TEST2(MSR_IA32_U_CET, CET_SHSTK_EN, CET_RESERVED, SHSTK, IBT), + MSR_TEST2(MSR_IA32_U_CET, CET_ENDBR_EN, CET_RESERVED, IBT, SHSTK), + MSR_TEST_CANONICAL(MSR_IA32_PL0_SSP, SHSTK), + MSR_TEST(MSR_IA32_PL0_SSP, canonical_val, canonical_val | 1, SHSTK), + MSR_TEST_CANONICAL(MSR_IA32_PL1_SSP, SHSTK), + MSR_TEST(MSR_IA32_PL1_SSP, canonical_val, canonical_val | 1, SHSTK), + MSR_TEST_CANONICAL(MSR_IA32_PL2_SSP, SHSTK), + MSR_TEST(MSR_IA32_PL2_SSP, canonical_val, canonical_val | 1, SHSTK), + MSR_TEST_CANONICAL(MSR_IA32_PL3_SSP, SHSTK), + MSR_TEST(MSR_IA32_PL3_SSP, canonical_val, canonical_val | 1, SHSTK), + + MSR_TEST_KVM(GUEST_SSP, canonical_val, NONCANONICAL, SHSTK), + }; + + const struct kvm_x86_cpu_feature feat_none = X86_FEATURE_NONE; + const struct kvm_x86_cpu_feature feat_lm = X86_FEATURE_LM; + + /* + * Create three vCPUs, but run them on the same task, to validate KVM's + * context switching of MSR state. Don't pin the task to a pCPU to + * also validate KVM's handling of cross-pCPU migration. Use the full + * set of features for the first two vCPUs, but clear all features in + * third vCPU in order to test both positive and negative paths. + */ + const int NR_VCPUS = 3; + struct kvm_vcpu *vcpus[NR_VCPUS]; + struct kvm_vm *vm; + int i; + + kvm_static_assert(sizeof(__msrs) <= sizeof(msrs)); + kvm_static_assert(ARRAY_SIZE(__msrs) <= ARRAY_SIZE(msrs)); + memcpy(msrs, __msrs, sizeof(__msrs)); + + ignore_unsupported_msrs = kvm_is_ignore_msrs(); + + vm = vm_create_with_vcpus(NR_VCPUS, guest_main, vcpus); + + sync_global_to_guest(vm, msrs); + sync_global_to_guest(vm, ignore_unsupported_msrs); + + /* + * Clear features in the "unsupported features" vCPU. This needs to be + * done before the first vCPU run as KVM's ABI is that guest CPUID is + * immutable once the vCPU has been run. + */ + for (idx = 0; idx < ARRAY_SIZE(__msrs); idx++) { + /* + * Don't clear LM; selftests are 64-bit only, and KVM doesn't + * honor LM=0 for MSRs that are supposed to exist if and only + * if the vCPU is a 64-bit model. Ditto for NONE; clearing a + * fake feature flag will result in false failures. + */ + if (memcmp(&msrs[idx].feature, &feat_lm, sizeof(feat_lm)) && + memcmp(&msrs[idx].feature, &feat_none, sizeof(feat_none))) + vcpu_clear_cpuid_feature(vcpus[2], msrs[idx].feature); + } + + for (idx = 0; idx < ARRAY_SIZE(__msrs); idx++) { + struct kvm_msr *msr = &msrs[idx]; + + if (msr->is_kvm_defined) { + for (i = 0; i < NR_VCPUS; i++) + host_test_kvm_reg(vcpus[i]); + continue; + } + + /* + * Verify KVM_GET_SUPPORTED_CPUID and KVM_GET_MSR_INDEX_LIST + * are consistent with respect to MSRs whose existence is + * enumerated via CPUID. Skip the check for FS/GS.base MSRs, + * as they aren't reported in the save/restore list since their + * state is managed via SREGS. + */ + TEST_ASSERT(msr->index == MSR_FS_BASE || msr->index == MSR_GS_BASE || + kvm_msr_is_in_save_restore_list(msr->index) == + (kvm_cpu_has(msr->feature) || kvm_cpu_has(msr->feature2)), + "%s %s in save/restore list, but %s according to CPUID", msr->name, + kvm_msr_is_in_save_restore_list(msr->index) ? "is" : "isn't", + (kvm_cpu_has(msr->feature) || kvm_cpu_has(msr->feature2)) ? + "supported" : "unsupported"); + + sync_global_to_guest(vm, idx); + + vcpus_run(vcpus, NR_VCPUS); + vcpus_run(vcpus, NR_VCPUS); + } + + kvm_vm_free(vm); +} + +int main(void) +{ + has_one_reg = kvm_has_cap(KVM_CAP_ONE_REG); + + test_msrs(); + + if (has_one_reg) { + use_one_reg = true; + test_msrs(); + } +} |