diff options
Diffstat (limited to 'arch/x86/kvm/vmx/vmx.c')
-rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 725 |
1 files changed, 371 insertions, 354 deletions
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 50810d471462..4bceb5ca3a89 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -36,6 +36,7 @@ #include <asm/debugreg.h> #include <asm/desc.h> #include <asm/fpu/internal.h> +#include <asm/idtentry.h> #include <asm/io.h> #include <asm/irq_remapping.h> #include <asm/kexec.h> @@ -57,6 +58,7 @@ #include "mmu.h" #include "nested.h" #include "pmu.h" +#include "sgx.h" #include "trace.h" #include "vmcs.h" #include "vmcs12.h" @@ -156,9 +158,11 @@ static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = { MSR_IA32_SPEC_CTRL, MSR_IA32_PRED_CMD, MSR_IA32_TSC, +#ifdef CONFIG_X86_64 MSR_FS_BASE, MSR_GS_BASE, MSR_KERNEL_GS_BASE, +#endif MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, @@ -361,8 +365,6 @@ static const struct kernel_param_ops vmentry_l1d_flush_ops = { module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644); static u32 vmx_segment_access_rights(struct kvm_segment *var); -static __always_inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, - u32 msr, int type); void vmx_vmexit(void); @@ -453,45 +455,10 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static unsigned long host_idt_base; -/* - * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm - * will emulate SYSCALL in legacy mode if the vendor string in guest - * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To - * support this emulation, IA32_STAR must always be included in - * vmx_uret_msrs_list[], even in i386 builds. - */ -static const u32 vmx_uret_msrs_list[] = { -#ifdef CONFIG_X86_64 - MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, -#endif - MSR_EFER, MSR_TSC_AUX, MSR_STAR, - MSR_IA32_TSX_CTRL, -}; - #if IS_ENABLED(CONFIG_HYPERV) static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); -/* check_ept_pointer() should be under protection of ept_pointer_lock. */ -static void check_ept_pointer_match(struct kvm *kvm) -{ - struct kvm_vcpu *vcpu; - u64 tmp_eptp = INVALID_PAGE; - int i; - - kvm_for_each_vcpu(i, vcpu, kvm) { - if (!VALID_PAGE(tmp_eptp)) { - tmp_eptp = to_vmx(vcpu)->ept_pointer; - } else if (tmp_eptp != to_vmx(vcpu)->ept_pointer) { - to_kvm_vmx(kvm)->ept_pointers_match - = EPT_POINTERS_MISMATCH; - return; - } - } - - to_kvm_vmx(kvm)->ept_pointers_match = EPT_POINTERS_MATCH; -} - static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush, void *data) { @@ -501,47 +468,70 @@ static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush range->pages); } -static inline int __hv_remote_flush_tlb_with_range(struct kvm *kvm, - struct kvm_vcpu *vcpu, struct kvm_tlb_range *range) +static inline int hv_remote_flush_root_ept(hpa_t root_ept, + struct kvm_tlb_range *range) { - u64 ept_pointer = to_vmx(vcpu)->ept_pointer; - - /* - * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs address - * of the base of EPT PML4 table, strip off EPT configuration - * information. - */ if (range) - return hyperv_flush_guest_mapping_range(ept_pointer & PAGE_MASK, + return hyperv_flush_guest_mapping_range(root_ept, kvm_fill_hv_flush_list_func, (void *)range); else - return hyperv_flush_guest_mapping(ept_pointer & PAGE_MASK); + return hyperv_flush_guest_mapping(root_ept); } static int hv_remote_flush_tlb_with_range(struct kvm *kvm, struct kvm_tlb_range *range) { + struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); struct kvm_vcpu *vcpu; - int ret = 0, i; + int ret = 0, i, nr_unique_valid_roots; + hpa_t root; - spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock); + spin_lock(&kvm_vmx->hv_root_ept_lock); - if (to_kvm_vmx(kvm)->ept_pointers_match == EPT_POINTERS_CHECK) - check_ept_pointer_match(kvm); + if (!VALID_PAGE(kvm_vmx->hv_root_ept)) { + nr_unique_valid_roots = 0; - if (to_kvm_vmx(kvm)->ept_pointers_match != EPT_POINTERS_MATCH) { + /* + * Flush all valid roots, and see if all vCPUs have converged + * on a common root, in which case future flushes can skip the + * loop and flush the common root. + */ kvm_for_each_vcpu(i, vcpu, kvm) { - /* If ept_pointer is invalid pointer, bypass flush request. */ - if (VALID_PAGE(to_vmx(vcpu)->ept_pointer)) - ret |= __hv_remote_flush_tlb_with_range( - kvm, vcpu, range); + root = to_vmx(vcpu)->hv_root_ept; + if (!VALID_PAGE(root) || root == kvm_vmx->hv_root_ept) + continue; + + /* + * Set the tracked root to the first valid root. Keep + * this root for the entirety of the loop even if more + * roots are encountered as a low effort optimization + * to avoid flushing the same (first) root again. + */ + if (++nr_unique_valid_roots == 1) + kvm_vmx->hv_root_ept = root; + + if (!ret) + ret = hv_remote_flush_root_ept(root, range); + + /* + * Stop processing roots if a failure occurred and + * multiple valid roots have already been detected. + */ + if (ret && nr_unique_valid_roots > 1) + break; } + + /* + * The optimized flush of a single root can't be used if there + * are multiple valid roots (obviously). + */ + if (nr_unique_valid_roots > 1) + kvm_vmx->hv_root_ept = INVALID_PAGE; } else { - ret = __hv_remote_flush_tlb_with_range(kvm, - kvm_get_vcpu(kvm, 0), range); + ret = hv_remote_flush_root_ept(kvm_vmx->hv_root_ept, range); } - spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); + spin_unlock(&kvm_vmx->hv_root_ept_lock); return ret; } static int hv_remote_flush_tlb(struct kvm *kvm) @@ -559,7 +549,7 @@ static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) * evmcs in singe VM shares same assist page. */ if (!*p_hv_pa_pg) - *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL); + *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); if (!*p_hv_pa_pg) return -ENOMEM; @@ -576,6 +566,21 @@ static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) #endif /* IS_ENABLED(CONFIG_HYPERV) */ +static void hv_track_root_ept(struct kvm_vcpu *vcpu, hpa_t root_ept) +{ +#if IS_ENABLED(CONFIG_HYPERV) + struct kvm_vmx *kvm_vmx = to_kvm_vmx(vcpu->kvm); + + if (kvm_x86_ops.tlb_remote_flush == hv_remote_flush_tlb) { + spin_lock(&kvm_vmx->hv_root_ept_lock); + to_vmx(vcpu)->hv_root_ept = root_ept; + if (root_ept != kvm_vmx->hv_root_ept) + kvm_vmx->hv_root_ept = INVALID_PAGE; + spin_unlock(&kvm_vmx->hv_root_ept_lock); + } +#endif +} + /* * Comment's format: document - errata name - stepping - processor name. * Refer from @@ -677,21 +682,11 @@ static bool is_valid_passthrough_msr(u32 msr) return r; } -static inline int __vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) -{ - int i; - - for (i = 0; i < vmx->nr_uret_msrs; ++i) - if (vmx_uret_msrs_list[vmx->guest_uret_msrs[i].slot] == msr) - return i; - return -1; -} - struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) { int i; - i = __vmx_find_uret_msr(vmx, msr); + i = kvm_find_user_return_msr(msr); if (i >= 0) return &vmx->guest_uret_msrs[i]; return NULL; @@ -700,13 +695,14 @@ struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, struct vmx_uret_msr *msr, u64 data) { + unsigned int slot = msr - vmx->guest_uret_msrs; int ret = 0; u64 old_msr_data = msr->data; msr->data = data; - if (msr - vmx->guest_uret_msrs < vmx->nr_active_uret_msrs) { + if (msr->load_into_hardware) { preempt_disable(); - ret = kvm_set_user_return_msr(msr->slot, msr->data, msr->mask); + ret = kvm_set_user_return_msr(slot, msr->data, msr->mask); preempt_enable(); if (ret) msr->data = old_msr_data; @@ -1058,7 +1054,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx) return false; } - i = __vmx_find_uret_msr(vmx, MSR_EFER); + i = kvm_find_user_return_msr(MSR_EFER); if (i < 0) return false; @@ -1220,11 +1216,14 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) */ if (!vmx->guest_uret_msrs_loaded) { vmx->guest_uret_msrs_loaded = true; - for (i = 0; i < vmx->nr_active_uret_msrs; ++i) - kvm_set_user_return_msr(vmx->guest_uret_msrs[i].slot, + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + if (!vmx->guest_uret_msrs[i].load_into_hardware) + continue; + + kvm_set_user_return_msr(i, vmx->guest_uret_msrs[i].data, vmx->guest_uret_msrs[i].mask); - + } } if (vmx->nested.need_vmcs12_to_shadow_sync) @@ -1529,7 +1528,7 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) /* * MTCFreq, CycThresh and PSBFreq encodings check, any MSR write that - * utilize encodings marked reserved will casue a #GP fault. + * utilize encodings marked reserved will cause a #GP fault. */ value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc_periods); if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc) && @@ -1570,12 +1569,25 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int insn_len) { + /* + * Emulation of instructions in SGX enclaves is impossible as RIP does + * not point tthe failing instruction, and even if it did, the code + * stream is inaccessible. Inject #UD instead of exiting to userspace + * so that guest userspace can't DoS the guest simply by triggering + * emulation (enclaves are CPL3 only). + */ + if (to_vmx(vcpu)->exit_reason.enclave_mode) { + kvm_queue_exception(vcpu, UD_VECTOR); + return false; + } return true; } static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { + union vmx_exit_reason exit_reason = to_vmx(vcpu)->exit_reason; unsigned long rip, orig_rip; + u32 instr_len; /* * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on @@ -1586,9 +1598,33 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) * i.e. we end up advancing IP with some random value. */ if (!static_cpu_has(X86_FEATURE_HYPERVISOR) || - to_vmx(vcpu)->exit_reason.basic != EXIT_REASON_EPT_MISCONFIG) { + exit_reason.basic != EXIT_REASON_EPT_MISCONFIG) { + instr_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); + + /* + * Emulating an enclave's instructions isn't supported as KVM + * cannot access the enclave's memory or its true RIP, e.g. the + * vmcs.GUEST_RIP points at the exit point of the enclave, not + * the RIP that actually triggered the VM-Exit. But, because + * most instructions that cause VM-Exit will #UD in an enclave, + * most instruction-based VM-Exits simply do not occur. + * + * There are a few exceptions, notably the debug instructions + * INT1ICEBRK and INT3, as they are allowed in debug enclaves + * and generate #DB/#BP as expected, which KVM might intercept. + * But again, the CPU does the dirty work and saves an instr + * length of zero so VMMs don't shoot themselves in the foot. + * WARN if KVM tries to skip a non-zero length instruction on + * a VM-Exit from an enclave. + */ + if (!instr_len) + goto rip_updated; + + WARN(exit_reason.enclave_mode, + "KVM: skipping instruction after SGX enclave VM-Exit"); + orig_rip = kvm_rip_read(vcpu); - rip = orig_rip + vmcs_read32(VM_EXIT_INSTRUCTION_LEN); + rip = orig_rip + instr_len; #ifdef CONFIG_X86_64 /* * We need to mask out the high 32 bits of RIP if not in 64-bit @@ -1604,6 +1640,7 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) return 0; } +rip_updated: /* skipping an emulated instruction also counts */ vmx_set_interrupt_shadow(vcpu, 0); @@ -1693,19 +1730,16 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu) vmx_clear_hlt(vcpu); } -static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr) +static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr, + bool load_into_hardware) { - struct vmx_uret_msr tmp; - int from, to; + struct vmx_uret_msr *uret_msr; - from = __vmx_find_uret_msr(vmx, msr); - if (from < 0) + uret_msr = vmx_find_uret_msr(vmx, msr); + if (!uret_msr) return; - to = vmx->nr_active_uret_msrs++; - tmp = vmx->guest_uret_msrs[to]; - vmx->guest_uret_msrs[to] = vmx->guest_uret_msrs[from]; - vmx->guest_uret_msrs[from] = tmp; + uret_msr->load_into_hardware = load_into_hardware; } /* @@ -1715,29 +1749,42 @@ static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr) */ static void setup_msrs(struct vcpu_vmx *vmx) { - vmx->guest_uret_msrs_loaded = false; - vmx->nr_active_uret_msrs = 0; #ifdef CONFIG_X86_64 + bool load_syscall_msrs; + /* * The SYSCALL MSRs are only needed on long mode guests, and only * when EFER.SCE is set. */ - if (is_long_mode(&vmx->vcpu) && (vmx->vcpu.arch.efer & EFER_SCE)) { - vmx_setup_uret_msr(vmx, MSR_STAR); - vmx_setup_uret_msr(vmx, MSR_LSTAR); - vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK); - } + load_syscall_msrs = is_long_mode(&vmx->vcpu) && + (vmx->vcpu.arch.efer & EFER_SCE); + + vmx_setup_uret_msr(vmx, MSR_STAR, load_syscall_msrs); + vmx_setup_uret_msr(vmx, MSR_LSTAR, load_syscall_msrs); + vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK, load_syscall_msrs); #endif - if (update_transition_efer(vmx)) - vmx_setup_uret_msr(vmx, MSR_EFER); + vmx_setup_uret_msr(vmx, MSR_EFER, update_transition_efer(vmx)); - if (guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP)) - vmx_setup_uret_msr(vmx, MSR_TSC_AUX); + vmx_setup_uret_msr(vmx, MSR_TSC_AUX, + guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDPID)); - vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL); + /* + * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations of new + * kernel and old userspace. If those guests run on a tsx=off host, do + * allow guests to use TSX_CTRL, but don't change the value in hardware + * so that TSX remains always disabled. + */ + vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL, boot_cpu_has(X86_FEATURE_RTM)); if (cpu_has_vmx_msr_bitmap()) vmx_update_msr_bitmap(&vmx->vcpu); + + /* + * The set of MSRs to load may have changed, reload MSRs before the + * next VM-Enter. + */ + vmx->guest_uret_msrs_loaded = false; } static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) @@ -1865,6 +1912,13 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_FEAT_CTL: msr_info->data = vmx->msr_ia32_feature_control; break; + case MSR_IA32_SGXLEPUBKEYHASH0 ... MSR_IA32_SGXLEPUBKEYHASH3: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC)) + return 1; + msr_info->data = to_vmx(vcpu)->msr_ia32_sgxlepubkeyhash + [msr_info->index - MSR_IA32_SGXLEPUBKEYHASH0]; + break; case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: if (!nested_vmx_allowed(vcpu)) return 1; @@ -1928,11 +1982,6 @@ static 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_TSC_AUX: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; - goto find_uret_msr; case MSR_IA32_DEBUGCTLMSR: msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); break; @@ -1966,6 +2015,9 @@ static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu) if (!intel_pmu_lbr_is_enabled(vcpu)) debugctl &= ~DEBUGCTLMSR_LBR_MASK; + if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) + debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT; + return debugctl; } @@ -2158,6 +2210,29 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmx->msr_ia32_feature_control = data; if (msr_info->host_initiated && data == 0) vmx_leave_nested(vcpu); + + /* SGX may be enabled/disabled by guest's firmware */ + vmx_write_encls_bitmap(vcpu, NULL); + break; + case MSR_IA32_SGXLEPUBKEYHASH0 ... MSR_IA32_SGXLEPUBKEYHASH3: + /* + * On real hardware, the LE hash MSRs are writable before + * the firmware sets bit 0 in MSR 0x7a ("activating" SGX), + * at which point SGX related bits in IA32_FEATURE_CONTROL + * become writable. + * + * KVM does not emulate SGX activation for simplicity, so + * allow writes to the LE hash MSRs if IA32_FEATURE_CONTROL + * is unlocked. This is technically not architectural + * behavior, but it's close enough. + */ + if (!msr_info->host_initiated && + (!guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC) || + ((vmx->msr_ia32_feature_control & FEAT_CTL_LOCKED) && + !(vmx->msr_ia32_feature_control & FEAT_CTL_SGX_LC_ENABLED)))) + return 1; + vmx->msr_ia32_sgxlepubkeyhash + [msr_index - MSR_IA32_SGXLEPUBKEYHASH0] = data; break; case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: if (!msr_info->host_initiated) @@ -2225,14 +2300,6 @@ static 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_TSC_AUX: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; - /* Check reserved bit, higher 32 bits should be zero */ - if ((data >> 32) != 0) - return 1; - goto find_uret_msr; case MSR_IA32_PERF_CAPABILITIES: if (data && !vcpu_to_pmu(vcpu)->version) return 1; @@ -2761,7 +2828,7 @@ static void enter_pmode(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); /* - * Update real mode segment cache. It may be not up-to-date if sement + * Update real mode segment cache. It may be not up-to-date if segment * register was written while vcpu was in a guest mode. */ vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); @@ -3088,8 +3155,7 @@ static int vmx_get_max_tdp_level(void) return 4; } -u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa, - int root_level) +u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) { u64 eptp = VMX_EPTP_MT_WB; @@ -3098,13 +3164,13 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa, if (enable_ept_ad_bits && (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu))) eptp |= VMX_EPTP_AD_ENABLE_BIT; - eptp |= (root_hpa & PAGE_MASK); + eptp |= root_hpa; return eptp; } -static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd, - int pgd_level) +static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, + int root_level) { struct kvm *kvm = vcpu->kvm; bool update_guest_cr3 = true; @@ -3112,16 +3178,10 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd, u64 eptp; if (enable_ept) { - eptp = construct_eptp(vcpu, pgd, pgd_level); + eptp = construct_eptp(vcpu, root_hpa, root_level); vmcs_write64(EPT_POINTER, eptp); - if (kvm_x86_ops.tlb_remote_flush) { - spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock); - to_vmx(vcpu)->ept_pointer = eptp; - to_kvm_vmx(kvm)->ept_pointers_match - = EPT_POINTERS_CHECK; - spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); - } + hv_track_root_ept(vcpu, root_hpa); if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; @@ -3131,7 +3191,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd, update_guest_cr3 = false; vmx_ept_load_pdptrs(vcpu); } else { - guest_cr3 = pgd; + guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu); } if (update_guest_cr3) @@ -3738,8 +3798,7 @@ static void vmx_set_msr_bitmap_write(ulong *msr_bitmap, u32 msr) __set_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); } -static __always_inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, - u32 msr, int type) +void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; @@ -3784,8 +3843,7 @@ static __always_inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, vmx_clear_msr_bitmap_write(msr_bitmap, msr); } -static __always_inline void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, - u32 msr, int type) +void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; @@ -3818,15 +3876,6 @@ static __always_inline void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, vmx_set_msr_bitmap_write(msr_bitmap, msr); } -void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, - u32 msr, int type, bool value) -{ - if (value) - vmx_enable_intercept_for_msr(vcpu, msr, type); - else - vmx_disable_intercept_for_msr(vcpu, msr, type); -} - static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) { u8 mode = 0; @@ -4299,7 +4348,23 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) xsaves_enabled, false); } - vmx_adjust_sec_exec_feature(vmx, &exec_control, rdtscp, RDTSCP); + /* + * RDPID is also gated by ENABLE_RDTSCP, turn on the control if either + * feature is exposed to the guest. This creates a virtualization hole + * if both are supported in hardware but only one is exposed to the + * guest, but letting the guest execute RDTSCP or RDPID when either one + * is advertised is preferable to emulating the advertised instruction + * in KVM on #UD, and obviously better than incorrectly injecting #UD. + */ + if (cpu_has_vmx_rdtscp()) { + bool rdpid_or_rdtscp_enabled = + guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + + vmx_adjust_secondary_exec_control(vmx, &exec_control, + SECONDARY_EXEC_ENABLE_RDTSCP, + rdpid_or_rdtscp_enabled, false); + } vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND); @@ -4314,15 +4379,6 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) vmx->secondary_exec_control = exec_control; } -static void ept_set_mmio_spte_mask(void) -{ - /* - * EPT Misconfigurations can be generated if the value of bits 2:0 - * of an EPT paging-structure entry is 110b (write/execute). - */ - kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE, 0); -} - #define VMX_XSS_EXIT_BITMAP 0 /* @@ -4410,8 +4466,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); } - if (cpu_has_vmx_encls_vmexit()) - vmcs_write64(ENCLS_EXITING_BITMAP, -1ull); + vmx_write_encls_bitmap(&vmx->vcpu, NULL); if (vmx_pt_mode_is_host_guest()) { memset(&vmx->pt_desc, 0, sizeof(vmx->pt_desc)); @@ -5020,7 +5075,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) reg = (exit_qualification >> 8) & 15; switch ((exit_qualification >> 4) & 3) { case 0: /* mov to cr */ - val = kvm_register_readl(vcpu, reg); + val = kvm_register_read(vcpu, reg); trace_kvm_cr_write(cr, val); switch (cr) { case 0: @@ -5143,7 +5198,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) kvm_register_write(vcpu, reg, val); err = 0; } else { - err = kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg)); + err = kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg)); } out: @@ -5184,17 +5239,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu) return 1; } -static int handle_vmcall(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_hypercall(vcpu); -} - -static int handle_invd(struct kvm_vcpu *vcpu) -{ - /* Treat an INVD instruction as a NOP and just skip it. */ - return kvm_skip_emulated_instruction(vcpu); -} - static int handle_invlpg(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmx_get_exit_qual(vcpu); @@ -5203,28 +5247,6 @@ static int handle_invlpg(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } -static int handle_rdpmc(struct kvm_vcpu *vcpu) -{ - int err; - - err = kvm_rdpmc(vcpu); - return kvm_complete_insn_gp(vcpu, err); -} - -static int handle_wbinvd(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_wbinvd(vcpu); -} - -static int handle_xsetbv(struct kvm_vcpu *vcpu) -{ - u64 new_bv = kvm_read_edx_eax(vcpu); - u32 index = kvm_rcx_read(vcpu); - - int err = kvm_set_xcr(vcpu, index, new_bv); - return kvm_complete_insn_gp(vcpu, err); -} - static int handle_apic_access(struct kvm_vcpu *vcpu) { if (likely(fasteoi)) { @@ -5361,7 +5383,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) EPT_VIOLATION_EXECUTABLE)) ? PFERR_PRESENT_MASK : 0; - error_code |= (exit_qualification & 0x100) != 0 ? + error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ? PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; vcpu->arch.exit_qualification = exit_qualification; @@ -5384,6 +5406,9 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { gpa_t gpa; + if (!vmx_can_emulate_instruction(vcpu, NULL, 0)) + return 1; + /* * A nested guest cannot optimize MMIO vmexits, because we have an * nGPA here instead of the required GPA. @@ -5485,18 +5510,6 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) } } -static void vmx_enable_tdp(void) -{ - kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, - enable_ept_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull, - enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull, - 0ull, VMX_EPT_EXECUTABLE_MASK, - cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK, - VMX_EPT_RWX_MASK, 0ull); - - ept_set_mmio_spte_mask(); -} - /* * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE * exiting, so only get here on cpu with PAUSE-Loop-Exiting. @@ -5516,34 +5529,11 @@ static int handle_pause(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } -static int handle_nop(struct kvm_vcpu *vcpu) -{ - return kvm_skip_emulated_instruction(vcpu); -} - -static int handle_mwait(struct kvm_vcpu *vcpu) -{ - printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n"); - return handle_nop(vcpu); -} - -static int handle_invalid_op(struct kvm_vcpu *vcpu) -{ - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; -} - static int handle_monitor_trap(struct kvm_vcpu *vcpu) { return 1; } -static int handle_monitor(struct kvm_vcpu *vcpu) -{ - printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); - return handle_nop(vcpu); -} - static int handle_invpcid(struct kvm_vcpu *vcpu) { u32 vmx_instruction_info; @@ -5560,7 +5550,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) } vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf); + type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); if (type > 3) { kvm_inject_gp(vcpu, 0); @@ -5632,16 +5622,18 @@ static int handle_vmx_instruction(struct kvm_vcpu *vcpu) return 1; } +#ifndef CONFIG_X86_SGX_KVM static int handle_encls(struct kvm_vcpu *vcpu) { /* - * SGX virtualization is not yet supported. There is no software - * enable bit for SGX, so we have to trap ENCLS and inject a #UD - * to prevent the guest from executing ENCLS. + * SGX virtualization is disabled. There is no software enable bit for + * SGX, so KVM intercepts all ENCLS leafs and injects a #UD to prevent + * the guest from executing ENCLS (when SGX is supported by hardware). */ kvm_queue_exception(vcpu, UD_VECTOR); return 1; } +#endif /* CONFIG_X86_SGX_KVM */ static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu) { @@ -5668,10 +5660,10 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_MSR_WRITE] = kvm_emulate_wrmsr, [EXIT_REASON_INTERRUPT_WINDOW] = handle_interrupt_window, [EXIT_REASON_HLT] = kvm_emulate_halt, - [EXIT_REASON_INVD] = handle_invd, + [EXIT_REASON_INVD] = kvm_emulate_invd, [EXIT_REASON_INVLPG] = handle_invlpg, - [EXIT_REASON_RDPMC] = handle_rdpmc, - [EXIT_REASON_VMCALL] = handle_vmcall, + [EXIT_REASON_RDPMC] = kvm_emulate_rdpmc, + [EXIT_REASON_VMCALL] = kvm_emulate_hypercall, [EXIT_REASON_VMCLEAR] = handle_vmx_instruction, [EXIT_REASON_VMLAUNCH] = handle_vmx_instruction, [EXIT_REASON_VMPTRLD] = handle_vmx_instruction, @@ -5685,8 +5677,8 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_APIC_ACCESS] = handle_apic_access, [EXIT_REASON_APIC_WRITE] = handle_apic_write, [EXIT_REASON_EOI_INDUCED] = handle_apic_eoi_induced, - [EXIT_REASON_WBINVD] = handle_wbinvd, - [EXIT_REASON_XSETBV] = handle_xsetbv, + [EXIT_REASON_WBINVD] = kvm_emulate_wbinvd, + [EXIT_REASON_XSETBV] = kvm_emulate_xsetbv, [EXIT_REASON_TASK_SWITCH] = handle_task_switch, [EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check, [EXIT_REASON_GDTR_IDTR] = handle_desc, @@ -5694,13 +5686,13 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, - [EXIT_REASON_MWAIT_INSTRUCTION] = handle_mwait, + [EXIT_REASON_MWAIT_INSTRUCTION] = kvm_emulate_mwait, [EXIT_REASON_MONITOR_TRAP_FLAG] = handle_monitor_trap, - [EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor, + [EXIT_REASON_MONITOR_INSTRUCTION] = kvm_emulate_monitor, [EXIT_REASON_INVEPT] = handle_vmx_instruction, [EXIT_REASON_INVVPID] = handle_vmx_instruction, - [EXIT_REASON_RDRAND] = handle_invalid_op, - [EXIT_REASON_RDSEED] = handle_invalid_op, + [EXIT_REASON_RDRAND] = kvm_handle_invalid_op, + [EXIT_REASON_RDSEED] = kvm_handle_invalid_op, [EXIT_REASON_PML_FULL] = handle_pml_full, [EXIT_REASON_INVPCID] = handle_invpcid, [EXIT_REASON_VMFUNC] = handle_vmx_instruction, @@ -5787,12 +5779,23 @@ static void vmx_dump_dtsel(char *name, uint32_t limit) vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT)); } -void dump_vmcs(void) +static void vmx_dump_msrs(char *name, struct vmx_msrs *m) { + unsigned int i; + struct vmx_msr_entry *e; + + pr_err("MSR %s:\n", name); + for (i = 0, e = m->val; i < m->nr; ++i, ++e) + pr_err(" %2d: msr=0x%08x value=0x%016llx\n", i, e->index, e->value); +} + +void dump_vmcs(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); u32 vmentry_ctl, vmexit_ctl; u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control; unsigned long cr4; - u64 efer; + int efer_slot; if (!dump_invalid_vmcs) { pr_warn_ratelimited("set kvm_intel.dump_invalid_vmcs=1 to dump internal KVM state.\n"); @@ -5804,7 +5807,6 @@ void dump_vmcs(void) cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL); cr4 = vmcs_readl(GUEST_CR4); - efer = vmcs_read64(GUEST_IA32_EFER); secondary_exec_control = 0; if (cpu_has_secondary_exec_ctrls()) secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); @@ -5816,9 +5818,7 @@ void dump_vmcs(void) pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK)); pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3)); - if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) && - (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA)) - { + if (cpu_has_vmx_ept()) { pr_err("PDPTR0 = 0x%016llx PDPTR1 = 0x%016llx\n", vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1)); pr_err("PDPTR2 = 0x%016llx PDPTR3 = 0x%016llx\n", @@ -5841,10 +5841,20 @@ void dump_vmcs(void) vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR); vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT); vmx_dump_sel("TR: ", GUEST_TR_SELECTOR); - if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) || - (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER))) - pr_err("EFER = 0x%016llx PAT = 0x%016llx\n", - efer, vmcs_read64(GUEST_IA32_PAT)); + efer_slot = vmx_find_loadstore_msr_slot(&vmx->msr_autoload.guest, MSR_EFER); + if (vmentry_ctl & VM_ENTRY_LOAD_IA32_EFER) + pr_err("EFER= 0x%016llx\n", vmcs_read64(GUEST_IA32_EFER)); + else if (efer_slot >= 0) + pr_err("EFER= 0x%016llx (autoload)\n", + vmx->msr_autoload.guest.val[efer_slot].value); + else if (vmentry_ctl & VM_ENTRY_IA32E_MODE) + pr_err("EFER= 0x%016llx (effective)\n", + vcpu->arch.efer | (EFER_LMA | EFER_LME)); + else + pr_err("EFER= 0x%016llx (effective)\n", + vcpu->arch.efer & ~(EFER_LMA | EFER_LME)); + if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PAT) + pr_err("PAT = 0x%016llx\n", vmcs_read64(GUEST_IA32_PAT)); pr_err("DebugCtl = 0x%016llx DebugExceptions = 0x%016lx\n", vmcs_read64(GUEST_IA32_DEBUGCTL), vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS)); @@ -5860,6 +5870,10 @@ void dump_vmcs(void) if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) pr_err("InterruptStatus = %04x\n", vmcs_read16(GUEST_INTR_STATUS)); + if (vmcs_read32(VM_ENTRY_MSR_LOAD_COUNT) > 0) + vmx_dump_msrs("guest autoload", &vmx->msr_autoload.guest); + if (vmcs_read32(VM_EXIT_MSR_STORE_COUNT) > 0) + vmx_dump_msrs("guest autostore", &vmx->msr_autostore.guest); pr_err("*** Host State ***\n"); pr_err("RIP = 0x%016lx RSP = 0x%016lx\n", @@ -5881,14 +5895,16 @@ void dump_vmcs(void) vmcs_readl(HOST_IA32_SYSENTER_ESP), vmcs_read32(HOST_IA32_SYSENTER_CS), vmcs_readl(HOST_IA32_SYSENTER_EIP)); - if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER)) - pr_err("EFER = 0x%016llx PAT = 0x%016llx\n", - vmcs_read64(HOST_IA32_EFER), - vmcs_read64(HOST_IA32_PAT)); + if (vmexit_ctl & VM_EXIT_LOAD_IA32_EFER) + pr_err("EFER= 0x%016llx\n", vmcs_read64(HOST_IA32_EFER)); + if (vmexit_ctl & VM_EXIT_LOAD_IA32_PAT) + pr_err("PAT = 0x%016llx\n", vmcs_read64(HOST_IA32_PAT)); if (cpu_has_load_perf_global_ctrl() && vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) pr_err("PerfGlobCtl = 0x%016llx\n", 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); pr_err("*** Control State ***\n"); pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n", @@ -5997,7 +6013,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) } if (exit_reason.failed_vmentry) { - dump_vmcs(); + dump_vmcs(vcpu); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason = exit_reason.full; @@ -6006,7 +6022,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) } if (unlikely(vmx->fail)) { - dump_vmcs(); + dump_vmcs(vcpu); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason = vmcs_read32(VM_INSTRUCTION_ERROR); @@ -6027,19 +6043,19 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) exit_reason.basic != EXIT_REASON_PML_FULL && exit_reason.basic != EXIT_REASON_APIC_ACCESS && exit_reason.basic != EXIT_REASON_TASK_SWITCH)) { + int ndata = 3; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; - vcpu->run->internal.ndata = 3; vcpu->run->internal.data[0] = vectoring_info; vcpu->run->internal.data[1] = exit_reason.full; vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { - vcpu->run->internal.ndata++; - vcpu->run->internal.data[3] = + vcpu->run->internal.data[ndata++] = vmcs_read64(GUEST_PHYSICAL_ADDRESS); } - vcpu->run->internal.data[vcpu->run->internal.ndata++] = - vcpu->arch.last_vmentry_cpu; + vcpu->run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu; + vcpu->run->internal.ndata = ndata; return 0; } @@ -6092,7 +6108,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) unexpected_vmexit: vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", exit_reason.full); - dump_vmcs(); + dump_vmcs(vcpu); vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; @@ -6395,18 +6411,17 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) void vmx_do_interrupt_nmi_irqoff(unsigned long entry); -static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu, u32 intr_info) +static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu, + unsigned long entry) { - unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; - gate_desc *desc = (gate_desc *)host_idt_base + vector; - kvm_before_interrupt(vcpu); - vmx_do_interrupt_nmi_irqoff(gate_offset(desc)); + vmx_do_interrupt_nmi_irqoff(entry); kvm_after_interrupt(vcpu); } static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) { + const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist; u32 intr_info = vmx_get_intr_info(&vmx->vcpu); /* if exit due to PF check for async PF */ @@ -6417,18 +6432,20 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) kvm_machine_check(); /* We need to handle NMIs before interrupts are enabled */ else if (is_nmi(intr_info)) - handle_interrupt_nmi_irqoff(&vmx->vcpu, intr_info); + handle_interrupt_nmi_irqoff(&vmx->vcpu, nmi_entry); } static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) { u32 intr_info = vmx_get_intr_info(vcpu); + unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; + gate_desc *desc = (gate_desc *)host_idt_base + vector; if (WARN_ONCE(!is_external_intr(intr_info), "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; - handle_interrupt_nmi_irqoff(vcpu, intr_info); + handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc)); } static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) @@ -6580,8 +6597,8 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) int i, nr_msrs; struct perf_guest_switch_msr *msrs; + /* Note, nr_msrs may be garbage if perf_guest_get_msrs() returns NULL. */ msrs = perf_guest_get_msrs(&nr_msrs); - if (!msrs) return; @@ -6642,25 +6659,7 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - /* - * VMENTER enables interrupts (host state), but the kernel state is - * interrupts disabled when this is invoked. Also tell RCU about - * it. This is the same logic as for exit_to_user_mode(). - * - * This ensures that e.g. latency analysis on the host observes - * guest mode as interrupt enabled. - * - * guest_enter_irqoff() informs context tracking about the - * transition to guest mode and if enabled adjusts RCU state - * accordingly. - */ - instrumentation_begin(); - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); - instrumentation_end(); - - guest_enter_irqoff(); - lockdep_hardirqs_on(CALLER_ADDR0); + kvm_guest_enter_irqoff(); /* L1D Flush includes CPU buffer clear to mitigate MDS */ if (static_branch_unlikely(&vmx_l1d_should_flush)) @@ -6676,24 +6675,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vcpu->arch.cr2 = native_read_cr2(); - /* - * VMEXIT disables interrupts (host state), but tracing and lockdep - * have them in state 'on' as recorded before entering guest mode. - * Same as enter_from_user_mode(). - * - * guest_exit_irqoff() restores host context and reinstates RCU if - * enabled and required. - * - * This needs to be done before the below as native_read_msr() - * contains a tracepoint and x86_spec_ctrl_restore_host() calls - * into world and some more. - */ - lockdep_hardirqs_off(CALLER_ADDR0); - guest_exit_irqoff(); - - instrumentation_begin(); - trace_hardirqs_off_finish(); - instrumentation_end(); + kvm_guest_exit_irqoff(); } static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) @@ -6868,6 +6850,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) static int vmx_create_vcpu(struct kvm_vcpu *vcpu) { + struct vmx_uret_msr *tsx_ctrl; struct vcpu_vmx *vmx; int i, cpu, err; @@ -6890,43 +6873,19 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) goto free_vpid; } - BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS); - - for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) { - u32 index = vmx_uret_msrs_list[i]; - u32 data_low, data_high; - int j = vmx->nr_uret_msrs; - - if (rdmsr_safe(index, &data_low, &data_high) < 0) - continue; - if (wrmsr_safe(index, data_low, data_high) < 0) - continue; - - vmx->guest_uret_msrs[j].slot = i; - vmx->guest_uret_msrs[j].data = 0; - switch (index) { - case MSR_IA32_TSX_CTRL: - /* - * TSX_CTRL_CPUID_CLEAR is handled in the CPUID - * interception. Keep the host value unchanged to avoid - * changing CPUID bits under the host kernel's feet. - * - * hle=0, rtm=0, tsx_ctrl=1 can be found with some - * combinations of new kernel and old userspace. If - * those guests run on a tsx=off host, do allow guests - * to use TSX_CTRL, but do not change the value on the - * host so that TSX remains always disabled. - */ - if (boot_cpu_has(X86_FEATURE_RTM)) - vmx->guest_uret_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; - else - vmx->guest_uret_msrs[j].mask = 0; - break; - default: - vmx->guest_uret_msrs[j].mask = -1ull; - break; - } - ++vmx->nr_uret_msrs; + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + vmx->guest_uret_msrs[i].data = 0; + vmx->guest_uret_msrs[i].mask = -1ull; + } + if (boot_cpu_has(X86_FEATURE_RTM)) { + /* + * TSX_CTRL_CPUID_CLEAR is handled in the CPUID interception. + * Keep the host value unchanged to avoid changing CPUID bits + * under the host kernel's feet. + */ + tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); + if (tsx_ctrl) + vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; } err = alloc_loaded_vmcs(&vmx->vmcs01); @@ -6938,9 +6897,11 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS); vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R); +#ifdef CONFIG_X86_64 vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); +#endif vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); @@ -6976,6 +6937,8 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) else memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); + vcpu_setup_sgx_lepubkeyhash(vcpu); + vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; @@ -6989,8 +6952,9 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) vmx->pi_desc.nv = POSTED_INTR_VECTOR; vmx->pi_desc.sn = 1; - vmx->ept_pointer = INVALID_PAGE; - +#if IS_ENABLED(CONFIG_HYPERV) + vmx->hv_root_ept = INVALID_PAGE; +#endif return 0; free_vmcs: @@ -7007,7 +6971,9 @@ free_vpid: static int vmx_vm_init(struct kvm *kvm) { - spin_lock_init(&to_kvm_vmx(kvm)->ept_pointer_lock); +#if IS_ENABLED(CONFIG_HYPERV) + spin_lock_init(&to_kvm_vmx(kvm)->hv_root_ept_lock); +#endif if (!ple_gap) kvm->arch.pause_in_guest = true; @@ -7252,7 +7218,7 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_TOPA; - /* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabircEn can be set */ + /* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabricEn can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_output_subsys)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN; @@ -7302,6 +7268,19 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) set_cr4_guest_host_mask(vmx); + vmx_write_encls_bitmap(vcpu, NULL); + if (guest_cpuid_has(vcpu, X86_FEATURE_SGX)) + vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_SGX_ENABLED; + else + vmx->msr_ia32_feature_control_valid_bits &= ~FEAT_CTL_SGX_ENABLED; + + if (guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC)) + vmx->msr_ia32_feature_control_valid_bits |= + FEAT_CTL_SGX_LC_ENABLED; + else + vmx->msr_ia32_feature_control_valid_bits &= + ~FEAT_CTL_SGX_LC_ENABLED; + /* Refresh #PF interception to account for MAXPHYADDR changes. */ vmx_update_exception_bitmap(vcpu); } @@ -7322,6 +7301,13 @@ static __init void vmx_set_cpu_caps(void) if (vmx_pt_mode_is_host_guest()) kvm_cpu_cap_check_and_set(X86_FEATURE_INTEL_PT); + if (!enable_sgx) { + kvm_cpu_cap_clear(X86_FEATURE_SGX); + kvm_cpu_cap_clear(X86_FEATURE_SGX_LC); + kvm_cpu_cap_clear(X86_FEATURE_SGX1); + kvm_cpu_cap_clear(X86_FEATURE_SGX2); + } + if (vmx_umip_emulated()) kvm_cpu_cap_set(X86_FEATURE_UMIP); @@ -7330,9 +7316,11 @@ static __init void vmx_set_cpu_caps(void) if (!cpu_has_vmx_xsaves()) kvm_cpu_cap_clear(X86_FEATURE_XSAVES); - /* CPUID 0x80000001 */ - if (!cpu_has_vmx_rdtscp()) + /* CPUID 0x80000001 and 0x7 (RDPID) */ + if (!cpu_has_vmx_rdtscp()) { kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); + kvm_cpu_cap_clear(X86_FEATURE_RDPID); + } if (cpu_has_vmx_waitpkg()) kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); @@ -7388,8 +7376,9 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, /* * RDPID causes #UD if disabled through secondary execution controls. * Because it is marked as EmulateOnUD, we need to intercept it here. + * Note, RDPID is hidden behind ENABLE_RDTSCP. */ - case x86_intercept_rdtscp: + case x86_intercept_rdpid: if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_RDTSCP)) { exception->vector = UD_VECTOR; exception->error_code_valid = false; @@ -7755,17 +7744,42 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, }; +static __init void vmx_setup_user_return_msrs(void) +{ + + /* + * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm + * will emulate SYSCALL in legacy mode if the vendor string in guest + * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To + * support this emulation, MSR_STAR is included in the list for i386, + * but is never loaded into hardware. MSR_CSTAR is also never loaded + * into hardware and is here purely for emulation purposes. + */ + const u32 vmx_uret_msrs_list[] = { + #ifdef CONFIG_X86_64 + MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, + #endif + MSR_EFER, MSR_TSC_AUX, MSR_STAR, + MSR_IA32_TSX_CTRL, + }; + int i; + + BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS); + + for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) + kvm_add_user_return_msr(vmx_uret_msrs_list[i]); +} + static __init int hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; - int r, i, ept_lpage_level; + int r, ept_lpage_level; store_idt(&dt); host_idt_base = dt.address; - for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) - kvm_define_user_return_msr(i, vmx_uret_msrs_list[i]); + vmx_setup_user_return_msrs(); if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) return -EIO; @@ -7848,7 +7862,8 @@ static __init int hardware_setup(void) set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ if (enable_ept) - vmx_enable_tdp(); + kvm_mmu_set_ept_masks(enable_ept_ad_bits, + cpu_has_vmx_ept_execute_only()); if (!enable_ept) ept_lpage_level = 0; @@ -7909,6 +7924,8 @@ static __init int hardware_setup(void) if (!enable_ept || !cpu_has_vmx_intel_pt()) pt_mode = PT_MODE_SYSTEM; + setup_default_sgx_lepubkeyhash(); + if (nested) { nested_vmx_setup_ctls_msrs(&vmcs_config.nested, vmx_capability.ept); |