diff options
Diffstat (limited to 'arch/x86/kvm/vmx')
| -rw-r--r-- | arch/x86/kvm/vmx/capabilities.h | 10 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/common.h | 182 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/hyperv.c | 1 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/hyperv.h | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/hyperv_evmcs.h | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/main.c | 1113 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/nested.c | 480 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/nested.h | 30 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/pmu_intel.c | 115 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/pmu_intel.h | 28 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/posted_intr.c | 97 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/posted_intr.h | 101 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/sgx.c | 30 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/tdx.c | 3526 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/tdx.h | 204 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/tdx_arch.h | 167 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/tdx_errno.h | 40 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmcs.h | 5 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmcs12.h | 14 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 1570 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.h | 171 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx_onhyperv.h | 10 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx_ops.h | 36 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/x86_ops.h | 233 |
24 files changed, 6859 insertions, 1308 deletions
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 41a4533f9989..cb6588238f46 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -54,9 +54,7 @@ struct nested_vmx_msrs { }; struct vmcs_config { - int size; - u32 basic_cap; - u32 revision_id; + u64 basic; u32 pin_based_exec_ctrl; u32 cpu_based_exec_ctrl; u32 cpu_based_2nd_exec_ctrl; @@ -76,7 +74,7 @@ extern struct vmx_capability vmx_capability __ro_after_init; static inline bool cpu_has_vmx_basic_inout(void) { - return (((u64)vmcs_config.basic_cap << 32) & VMX_BASIC_INOUT); + return vmcs_config.basic & VMX_BASIC_INOUT; } static inline bool cpu_has_virtual_nmis(void) @@ -225,7 +223,7 @@ static inline bool cpu_has_vmx_vmfunc(void) static inline bool cpu_has_vmx_shadow_vmcs(void) { /* check if the cpu supports writing r/o exit information fields */ - if (!(vmcs_config.misc & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) + if (!(vmcs_config.misc & VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) return false; return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -367,7 +365,7 @@ static inline bool cpu_has_vmx_invvpid_global(void) static inline bool cpu_has_vmx_intel_pt(void) { - return (vmcs_config.misc & MSR_IA32_VMX_MISC_INTEL_PT) && + return (vmcs_config.misc & VMX_MISC_INTEL_PT) && (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PT_USE_GPA) && (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_RTIT_CTL); } diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h new file mode 100644 index 000000000000..8f46a06e2c44 --- /dev/null +++ b/arch/x86/kvm/vmx/common.h @@ -0,0 +1,182 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __KVM_X86_VMX_COMMON_H +#define __KVM_X86_VMX_COMMON_H + +#include <linux/kvm_host.h> +#include <asm/posted_intr.h> + +#include "mmu.h" + +union vmx_exit_reason { + struct { + u32 basic : 16; + u32 reserved16 : 1; + u32 reserved17 : 1; + u32 reserved18 : 1; + u32 reserved19 : 1; + u32 reserved20 : 1; + u32 reserved21 : 1; + u32 reserved22 : 1; + u32 reserved23 : 1; + u32 reserved24 : 1; + u32 reserved25 : 1; + u32 bus_lock_detected : 1; + u32 enclave_mode : 1; + u32 smi_pending_mtf : 1; + u32 smi_from_vmx_root : 1; + u32 reserved30 : 1; + u32 failed_vmentry : 1; + }; + u32 full; +}; + +struct vcpu_vt { + /* Posted interrupt descriptor */ + struct pi_desc pi_desc; + + /* Used if this vCPU is waiting for PI notification wakeup. */ + struct list_head pi_wakeup_list; + + union vmx_exit_reason exit_reason; + + unsigned long exit_qualification; + u32 exit_intr_info; + + /* + * If true, guest state has been loaded into hardware, and host state + * saved into vcpu_{vt,vmx,tdx}. If false, host state is loaded into + * hardware. + */ + bool guest_state_loaded; + bool emulation_required; + +#ifdef CONFIG_X86_64 + u64 msr_host_kernel_gs_base; +#endif + + unsigned long host_debugctlmsr; +}; + +#ifdef CONFIG_KVM_INTEL_TDX + +static __always_inline bool is_td(struct kvm *kvm) +{ + return kvm->arch.vm_type == KVM_X86_TDX_VM; +} + +static __always_inline bool is_td_vcpu(struct kvm_vcpu *vcpu) +{ + return is_td(vcpu->kvm); +} + +#else + +static inline bool is_td(struct kvm *kvm) { return false; } +static inline bool is_td_vcpu(struct kvm_vcpu *vcpu) { return false; } + +#endif + +static inline bool vt_is_tdx_private_gpa(struct kvm *kvm, gpa_t gpa) +{ + /* For TDX the direct mask is the shared mask. */ + return !kvm_is_addr_direct(kvm, gpa); +} + +static inline int __vmx_handle_ept_violation(struct kvm_vcpu *vcpu, gpa_t gpa, + unsigned long exit_qualification) +{ + u64 error_code; + + /* Is it a read fault? */ + error_code = (exit_qualification & EPT_VIOLATION_ACC_READ) + ? PFERR_USER_MASK : 0; + /* Is it a write fault? */ + error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE) + ? PFERR_WRITE_MASK : 0; + /* Is it a fetch fault? */ + error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR) + ? PFERR_FETCH_MASK : 0; + /* ept page table entry is present? */ + error_code |= (exit_qualification & EPT_VIOLATION_PROT_MASK) + ? PFERR_PRESENT_MASK : 0; + + if (error_code & EPT_VIOLATION_GVA_IS_VALID) + error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ? + PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; + + if (vt_is_tdx_private_gpa(vcpu->kvm, gpa)) + error_code |= PFERR_PRIVATE_ACCESS; + + return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); +} + +static inline void kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, + int pi_vec) +{ +#ifdef CONFIG_SMP + if (vcpu->mode == IN_GUEST_MODE) { + /* + * The vector of the virtual has already been set in the PIR. + * Send a notification event to deliver the virtual interrupt + * unless the vCPU is the currently running vCPU, i.e. the + * event is being sent from a fastpath VM-Exit handler, in + * which case the PIR will be synced to the vIRR before + * re-entering the guest. + * + * When the target is not the running vCPU, the following + * possibilities emerge: + * + * Case 1: vCPU stays in non-root mode. Sending a notification + * event posts the interrupt to the vCPU. + * + * Case 2: vCPU exits to root mode and is still runnable. The + * PIR will be synced to the vIRR before re-entering the guest. + * Sending a notification event is ok as the host IRQ handler + * will ignore the spurious event. + * + * Case 3: vCPU exits to root mode and is blocked. vcpu_block() + * has already synced PIR to vIRR and never blocks the vCPU if + * the vIRR is not empty. Therefore, a blocked vCPU here does + * not wait for any requested interrupts in PIR, and sending a + * notification event also results in a benign, spurious event. + */ + + if (vcpu != kvm_get_running_vcpu()) + __apic_send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec); + return; + } +#endif + /* + * The vCPU isn't in the guest; wake the vCPU in case it is blocking, + * otherwise do nothing as KVM will grab the highest priority pending + * IRQ via ->sync_pir_to_irr() in vcpu_enter_guest(). + */ + kvm_vcpu_wake_up(vcpu); +} + +/* + * Post an interrupt to a vCPU's PIR and trigger the vCPU to process the + * interrupt if necessary. + */ +static inline void __vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, + struct pi_desc *pi_desc, int vector) +{ + if (pi_test_and_set_pir(vector, pi_desc)) + return; + + /* If a previous notification has sent the IPI, nothing to do. */ + if (pi_test_and_set_on(pi_desc)) + return; + + /* + * The implied barrier in pi_test_and_set_on() pairs with the smp_mb_*() + * after setting vcpu->mode in vcpu_enter_guest(), thus the vCPU is + * guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a + * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE. + */ + kvm_vcpu_trigger_posted_interrupt(vcpu, POSTED_INTR_VECTOR); +} + +noinstr void vmx_handle_nmi(struct kvm_vcpu *vcpu); + +#endif /* __KVM_X86_VMX_COMMON_H */ diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index fab6a1ad98dc..fa41d036acd4 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -4,6 +4,7 @@ #include <linux/errno.h> #include <linux/smp.h> +#include "x86.h" #include "../cpuid.h" #include "hyperv.h" #include "nested.h" diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index a87407412615..11a339009781 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -42,7 +42,7 @@ static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx) return vmx->nested.hv_evmcs; } -static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu) +static inline bool guest_cpu_cap_has_evmcs(struct kvm_vcpu *vcpu) { /* * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.h b/arch/x86/kvm/vmx/hyperv_evmcs.h index a543fccfc574..6536290f4274 100644 --- a/arch/x86/kvm/vmx/hyperv_evmcs.h +++ b/arch/x86/kvm/vmx/hyperv_evmcs.h @@ -6,7 +6,7 @@ #ifndef __KVM_X86_VMX_HYPERV_EVMCS_H #define __KVM_X86_VMX_HYPERV_EVMCS_H -#include <asm/hyperv-tlfs.h> +#include <hyperv/hvhdk.h> #include "capabilities.h" #include "vmcs12.h" diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c new file mode 100644 index 000000000000..94d5d907d37b --- /dev/null +++ b/arch/x86/kvm/vmx/main.c @@ -0,0 +1,1113 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/moduleparam.h> + +#include "x86_ops.h" +#include "vmx.h" +#include "mmu.h" +#include "nested.h" +#include "pmu.h" +#include "posted_intr.h" +#include "tdx.h" +#include "tdx_arch.h" + +#ifdef CONFIG_KVM_INTEL_TDX +static_assert(offsetof(struct vcpu_vmx, vt) == offsetof(struct vcpu_tdx, vt)); +#endif + +static void vt_disable_virtualization_cpu(void) +{ + /* Note, TDX *and* VMX need to be disabled if TDX is enabled. */ + if (enable_tdx) + tdx_disable_virtualization_cpu(); + vmx_disable_virtualization_cpu(); +} + +static __init int vt_hardware_setup(void) +{ + int ret; + + ret = vmx_hardware_setup(); + if (ret) + return ret; + + /* + * Update vt_x86_ops::vm_size here so it is ready before + * kvm_ops_update() is called in kvm_x86_vendor_init(). + * + * Note, the actual bringing up of TDX must be done after + * kvm_ops_update() because enabling TDX requires enabling + * hardware virtualization first, i.e., all online CPUs must + * be in post-VMXON state. This means the @vm_size here + * may be updated to TDX's size but TDX may fail to enable + * at later time. + * + * The VMX/VT code could update kvm_x86_ops::vm_size again + * after bringing up TDX, but this would require exporting + * either kvm_x86_ops or kvm_ops_update() from the base KVM + * module, which looks overkill. Anyway, the worst case here + * is KVM may allocate couple of more bytes than needed for + * each VM. + */ + if (enable_tdx) { + vt_x86_ops.vm_size = max_t(unsigned int, vt_x86_ops.vm_size, + sizeof(struct kvm_tdx)); + /* + * Note, TDX may fail to initialize in a later time in + * vt_init(), in which case it is not necessary to setup + * those callbacks. But making them valid here even + * when TDX fails to init later is fine because those + * callbacks won't be called if the VM isn't TDX guest. + */ + vt_x86_ops.link_external_spt = tdx_sept_link_private_spt; + vt_x86_ops.set_external_spte = tdx_sept_set_private_spte; + vt_x86_ops.free_external_spt = tdx_sept_free_private_spt; + vt_x86_ops.remove_external_spte = tdx_sept_remove_private_spte; + vt_x86_ops.protected_apic_has_interrupt = tdx_protected_apic_has_interrupt; + } + + return 0; +} + +static int vt_vm_init(struct kvm *kvm) +{ + if (is_td(kvm)) + return tdx_vm_init(kvm); + + return vmx_vm_init(kvm); +} + +static void vt_vm_pre_destroy(struct kvm *kvm) +{ + if (is_td(kvm)) + return tdx_mmu_release_hkid(kvm); +} + +static void vt_vm_destroy(struct kvm *kvm) +{ + if (is_td(kvm)) + return tdx_vm_destroy(kvm); + + vmx_vm_destroy(kvm); +} + +static int vt_vcpu_precreate(struct kvm *kvm) +{ + if (is_td(kvm)) + return 0; + + return vmx_vcpu_precreate(kvm); +} + +static int vt_vcpu_create(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return tdx_vcpu_create(vcpu); + + return vmx_vcpu_create(vcpu); +} + +static void vt_vcpu_free(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) { + tdx_vcpu_free(vcpu); + return; + } + + vmx_vcpu_free(vcpu); +} + +static void vt_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) +{ + if (is_td_vcpu(vcpu)) { + tdx_vcpu_reset(vcpu, init_event); + return; + } + + vmx_vcpu_reset(vcpu, init_event); +} + +static void vt_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + if (is_td_vcpu(vcpu)) { + tdx_vcpu_load(vcpu, cpu); + return; + } + + vmx_vcpu_load(vcpu, cpu); +} + +static void vt_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) +{ + /* + * Basic TDX does not support feature PML. KVM does not enable PML in + * TD's VMCS, nor does it allocate or flush PML buffer for TDX. + */ + if (WARN_ON_ONCE(is_td_vcpu(vcpu))) + return; + + vmx_update_cpu_dirty_logging(vcpu); +} + +static void vt_prepare_switch_to_guest(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) { + tdx_prepare_switch_to_guest(vcpu); + return; + } + + vmx_prepare_switch_to_guest(vcpu); +} + +static void vt_vcpu_put(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) { + tdx_vcpu_put(vcpu); + return; + } + + vmx_vcpu_put(vcpu); +} + +static int vt_vcpu_pre_run(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return tdx_vcpu_pre_run(vcpu); + + return vmx_vcpu_pre_run(vcpu); +} + +static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) +{ + if (is_td_vcpu(vcpu)) + return tdx_vcpu_run(vcpu, force_immediate_exit); + + return vmx_vcpu_run(vcpu, force_immediate_exit); +} + +static int vt_handle_exit(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion fastpath) +{ + if (is_td_vcpu(vcpu)) + return tdx_handle_exit(vcpu, fastpath); + + return vmx_handle_exit(vcpu, fastpath); +} + +static int vt_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + if (unlikely(is_td_vcpu(vcpu))) + return tdx_set_msr(vcpu, msr_info); + + return vmx_set_msr(vcpu, msr_info); +} + +/* + * The kvm parameter can be NULL (module initialization, or invocation before + * VM creation). Be sure to check the kvm parameter before using it. + */ +static bool vt_has_emulated_msr(struct kvm *kvm, u32 index) +{ + if (kvm && is_td(kvm)) + return tdx_has_emulated_msr(index); + + return vmx_has_emulated_msr(kvm, index); +} + +static int vt_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + if (unlikely(is_td_vcpu(vcpu))) + return tdx_get_msr(vcpu, msr_info); + + return vmx_get_msr(vcpu, msr_info); +} + +static void vt_msr_filter_changed(struct kvm_vcpu *vcpu) +{ + /* + * TDX doesn't allow VMM to configure interception of MSR accesses. + * TDX guest requests MSR accesses by calling TDVMCALL. The MSR + * filters will be applied when handling the TDVMCALL for RDMSR/WRMSR + * if the userspace has set any. + */ + if (is_td_vcpu(vcpu)) + return; + + vmx_msr_filter_changed(vcpu); +} + +static int vt_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) +{ + if (is_td_vcpu(vcpu)) + return tdx_complete_emulated_msr(vcpu, err); + + return kvm_complete_insn_gp(vcpu, err); +} + +#ifdef CONFIG_KVM_SMM +static int vt_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +{ + if (KVM_BUG_ON(is_td_vcpu(vcpu), vcpu->kvm)) + return 0; + + return vmx_smi_allowed(vcpu, for_injection); +} + +static int vt_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) +{ + if (KVM_BUG_ON(is_td_vcpu(vcpu), vcpu->kvm)) + return 0; + + return vmx_enter_smm(vcpu, smram); +} + +static int vt_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) +{ + if (KVM_BUG_ON(is_td_vcpu(vcpu), vcpu->kvm)) + return 0; + + return vmx_leave_smm(vcpu, smram); +} + +static void vt_enable_smi_window(struct kvm_vcpu *vcpu) +{ + if (KVM_BUG_ON(is_td_vcpu(vcpu), vcpu->kvm)) + return; + + /* RSM will cause a vmexit anyway. */ + vmx_enable_smi_window(vcpu); +} +#endif + +static int vt_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) +{ + /* + * For TDX, this can only be triggered for MMIO emulation. Let the + * guest retry after installing the SPTE with suppress #VE bit cleared, + * so that the guest will receive #VE when retry. The guest is expected + * to call TDG.VP.VMCALL<MMIO> to request VMM to do MMIO emulation on + * #VE. + */ + if (is_td_vcpu(vcpu)) + return X86EMUL_RETRY_INSTR; + + return vmx_check_emulate_instruction(vcpu, emul_type, insn, insn_len); +} + +static bool vt_apic_init_signal_blocked(struct kvm_vcpu *vcpu) +{ + /* + * INIT and SIPI are always blocked for TDX, i.e., INIT handling and + * the OP vcpu_deliver_sipi_vector() won't be called. + */ + if (is_td_vcpu(vcpu)) + return true; + + return vmx_apic_init_signal_blocked(vcpu); +} + +static void vt_set_virtual_apic_mode(struct kvm_vcpu *vcpu) +{ + /* Only x2APIC mode is supported for TD. */ + if (is_td_vcpu(vcpu)) + return; + + return vmx_set_virtual_apic_mode(vcpu); +} + +static void vt_apicv_pre_state_restore(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi = vcpu_to_pi_desc(vcpu); + + pi_clear_on(pi); + memset(pi->pir, 0, sizeof(pi->pir)); +} + +static void vt_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) +{ + if (is_td_vcpu(vcpu)) + return; + + return vmx_hwapic_isr_update(vcpu, max_isr); +} + +static int vt_sync_pir_to_irr(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return -1; + + return vmx_sync_pir_to_irr(vcpu); +} + +static void vt_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) +{ + if (is_td_vcpu(apic->vcpu)) { + tdx_deliver_interrupt(apic, delivery_mode, trig_mode, + vector); + return; + } + + vmx_deliver_interrupt(apic, delivery_mode, trig_mode, vector); +} + +static void vt_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_vcpu_after_set_cpuid(vcpu); +} + +static void vt_update_exception_bitmap(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_update_exception_bitmap(vcpu); +} + +static u64 vt_get_segment_base(struct kvm_vcpu *vcpu, int seg) +{ + if (is_td_vcpu(vcpu)) + return 0; + + return vmx_get_segment_base(vcpu, seg); +} + +static void vt_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, + int seg) +{ + if (is_td_vcpu(vcpu)) { + memset(var, 0, sizeof(*var)); + return; + } + + vmx_get_segment(vcpu, var, seg); +} + +static void vt_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, + int seg) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_set_segment(vcpu, var, seg); +} + +static int vt_get_cpl(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return 0; + + return vmx_get_cpl(vcpu); +} + +static int vt_get_cpl_no_cache(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return 0; + + return vmx_get_cpl_no_cache(vcpu); +} + +static void vt_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) +{ + if (is_td_vcpu(vcpu)) { + *db = 0; + *l = 0; + return; + } + + vmx_get_cs_db_l_bits(vcpu, db, l); +} + +static bool vt_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +{ + if (is_td_vcpu(vcpu)) + return true; + + return vmx_is_valid_cr0(vcpu, cr0); +} + +static void vt_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_set_cr0(vcpu, cr0); +} + +static bool vt_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + if (is_td_vcpu(vcpu)) + return true; + + return vmx_is_valid_cr4(vcpu, cr4); +} + +static void vt_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_set_cr4(vcpu, cr4); +} + +static int vt_set_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + if (is_td_vcpu(vcpu)) + return 0; + + return vmx_set_efer(vcpu, efer); +} + +static void vt_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +{ + if (is_td_vcpu(vcpu)) { + memset(dt, 0, sizeof(*dt)); + return; + } + + vmx_get_idt(vcpu, dt); +} + +static void vt_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_set_idt(vcpu, dt); +} + +static void vt_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +{ + if (is_td_vcpu(vcpu)) { + memset(dt, 0, sizeof(*dt)); + return; + } + + vmx_get_gdt(vcpu, dt); +} + +static void vt_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_set_gdt(vcpu, dt); +} + +static void vt_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_set_dr6(vcpu, val); +} + +static void vt_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_set_dr7(vcpu, val); +} + +static void vt_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) +{ + /* + * MOV-DR exiting is always cleared for TD guest, even in debug mode. + * Thus KVM_DEBUGREG_WONT_EXIT can never be set and it should never + * reach here for TD vcpu. + */ + if (is_td_vcpu(vcpu)) + return; + + vmx_sync_dirty_debug_regs(vcpu); +} + +static void vt_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) +{ + if (WARN_ON_ONCE(is_td_vcpu(vcpu))) + return; + + vmx_cache_reg(vcpu, reg); +} + +static unsigned long vt_get_rflags(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return 0; + + return vmx_get_rflags(vcpu); +} + +static void vt_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_set_rflags(vcpu, rflags); +} + +static bool vt_get_if_flag(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return false; + + return vmx_get_if_flag(vcpu); +} + +static void vt_flush_tlb_all(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) { + tdx_flush_tlb_all(vcpu); + return; + } + + vmx_flush_tlb_all(vcpu); +} + +static void vt_flush_tlb_current(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) { + tdx_flush_tlb_current(vcpu); + return; + } + + vmx_flush_tlb_current(vcpu); +} + +static void vt_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_flush_tlb_gva(vcpu, addr); +} + +static void vt_flush_tlb_guest(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_flush_tlb_guest(vcpu); +} + +static void vt_inject_nmi(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) { + tdx_inject_nmi(vcpu); + return; + } + + vmx_inject_nmi(vcpu); +} + +static int vt_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +{ + /* + * The TDX module manages NMI windows and NMI reinjection, and hides NMI + * blocking, all KVM can do is throw an NMI over the wall. + */ + if (is_td_vcpu(vcpu)) + return true; + + return vmx_nmi_allowed(vcpu, for_injection); +} + +static bool vt_get_nmi_mask(struct kvm_vcpu *vcpu) +{ + /* + * KVM can't get NMI blocking status for TDX guest, assume NMIs are + * always unmasked. + */ + if (is_td_vcpu(vcpu)) + return false; + + return vmx_get_nmi_mask(vcpu); +} + +static void vt_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_set_nmi_mask(vcpu, masked); +} + +static void vt_enable_nmi_window(struct kvm_vcpu *vcpu) +{ + /* Refer to the comments in tdx_inject_nmi(). */ + if (is_td_vcpu(vcpu)) + return; + + vmx_enable_nmi_window(vcpu); +} + +static void vt_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, + int pgd_level) +{ + if (is_td_vcpu(vcpu)) { + tdx_load_mmu_pgd(vcpu, root_hpa, pgd_level); + return; + } + + vmx_load_mmu_pgd(vcpu, root_hpa, pgd_level); +} + +static void vt_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_set_interrupt_shadow(vcpu, mask); +} + +static u32 vt_get_interrupt_shadow(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return 0; + + return vmx_get_interrupt_shadow(vcpu); +} + +static void vt_patch_hypercall(struct kvm_vcpu *vcpu, + unsigned char *hypercall) +{ + /* + * Because guest memory is protected, guest can't be patched. TD kernel + * is modified to use TDG.VP.VMCALL for hypercall. + */ + if (is_td_vcpu(vcpu)) + return; + + vmx_patch_hypercall(vcpu, hypercall); +} + +static void vt_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_inject_irq(vcpu, reinjected); +} + +static void vt_inject_exception(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_inject_exception(vcpu); +} + +static void vt_cancel_injection(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_cancel_injection(vcpu); +} + +static int vt_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) +{ + if (is_td_vcpu(vcpu)) + return tdx_interrupt_allowed(vcpu); + + return vmx_interrupt_allowed(vcpu, for_injection); +} + +static void vt_enable_irq_window(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_enable_irq_window(vcpu); +} + +static void vt_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code) +{ + *intr_info = 0; + *error_code = 0; + + if (is_td_vcpu(vcpu)) + return; + + vmx_get_entry_info(vcpu, intr_info, error_code); +} + +static void vt_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code) +{ + if (is_td_vcpu(vcpu)) { + tdx_get_exit_info(vcpu, reason, info1, info2, intr_info, + error_code); + return; + } + + vmx_get_exit_info(vcpu, reason, info1, info2, intr_info, error_code); +} + +static void vt_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_update_cr8_intercept(vcpu, tpr, irr); +} + +static void vt_set_apic_access_page_addr(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_set_apic_access_page_addr(vcpu); +} + +static void vt_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) { + KVM_BUG_ON(!kvm_vcpu_apicv_active(vcpu), vcpu->kvm); + return; + } + + vmx_refresh_apicv_exec_ctrl(vcpu); +} + +static void vt_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_load_eoi_exitmap(vcpu, eoi_exit_bitmap); +} + +static int vt_set_tss_addr(struct kvm *kvm, unsigned int addr) +{ + if (is_td(kvm)) + return 0; + + return vmx_set_tss_addr(kvm, addr); +} + +static int vt_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) +{ + if (is_td(kvm)) + return 0; + + return vmx_set_identity_map_addr(kvm, ident_addr); +} + +static u64 vt_get_l2_tsc_offset(struct kvm_vcpu *vcpu) +{ + /* TDX doesn't support L2 guest at the moment. */ + if (is_td_vcpu(vcpu)) + return 0; + + return vmx_get_l2_tsc_offset(vcpu); +} + +static u64 vt_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) +{ + /* TDX doesn't support L2 guest at the moment. */ + if (is_td_vcpu(vcpu)) + return 0; + + return vmx_get_l2_tsc_multiplier(vcpu); +} + +static void vt_write_tsc_offset(struct kvm_vcpu *vcpu) +{ + /* In TDX, tsc offset can't be changed. */ + if (is_td_vcpu(vcpu)) + return; + + vmx_write_tsc_offset(vcpu); +} + +static void vt_write_tsc_multiplier(struct kvm_vcpu *vcpu) +{ + /* In TDX, tsc multiplier can't be changed. */ + if (is_td_vcpu(vcpu)) + return; + + vmx_write_tsc_multiplier(vcpu); +} + +#ifdef CONFIG_X86_64 +static int vt_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, + bool *expired) +{ + /* VMX-preemption timer isn't available for TDX. */ + if (is_td_vcpu(vcpu)) + return -EINVAL; + + return vmx_set_hv_timer(vcpu, guest_deadline_tsc, expired); +} + +static void vt_cancel_hv_timer(struct kvm_vcpu *vcpu) +{ + /* VMX-preemption timer can't be set. See vt_set_hv_timer(). */ + if (is_td_vcpu(vcpu)) + return; + + vmx_cancel_hv_timer(vcpu); +} +#endif + +static void vt_setup_mce(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_setup_mce(vcpu); +} + +static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp) +{ + if (!is_td(kvm)) + return -ENOTTY; + + return tdx_vm_ioctl(kvm, argp); +} + +static int vt_vcpu_mem_enc_ioctl(struct kvm_vcpu *vcpu, void __user *argp) +{ + if (!is_td_vcpu(vcpu)) + return -EINVAL; + + return tdx_vcpu_ioctl(vcpu, argp); +} + +static int vt_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) +{ + if (is_td(kvm)) + return tdx_gmem_private_max_mapping_level(kvm, pfn); + + return 0; +} + +#define VMX_REQUIRED_APICV_INHIBITS \ + (BIT(APICV_INHIBIT_REASON_DISABLED) | \ + BIT(APICV_INHIBIT_REASON_ABSENT) | \ + BIT(APICV_INHIBIT_REASON_HYPERV) | \ + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ + BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED)) + +struct kvm_x86_ops vt_x86_ops __initdata = { + .name = KBUILD_MODNAME, + + .check_processor_compatibility = vmx_check_processor_compat, + + .hardware_unsetup = vmx_hardware_unsetup, + + .enable_virtualization_cpu = vmx_enable_virtualization_cpu, + .disable_virtualization_cpu = vt_disable_virtualization_cpu, + .emergency_disable_virtualization_cpu = vmx_emergency_disable_virtualization_cpu, + + .has_emulated_msr = vt_has_emulated_msr, + + .vm_size = sizeof(struct kvm_vmx), + + .vm_init = vt_vm_init, + .vm_pre_destroy = vt_vm_pre_destroy, + .vm_destroy = vt_vm_destroy, + + .vcpu_precreate = vt_vcpu_precreate, + .vcpu_create = vt_vcpu_create, + .vcpu_free = vt_vcpu_free, + .vcpu_reset = vt_vcpu_reset, + + .prepare_switch_to_guest = vt_prepare_switch_to_guest, + .vcpu_load = vt_vcpu_load, + .vcpu_put = vt_vcpu_put, + + .update_exception_bitmap = vt_update_exception_bitmap, + .get_feature_msr = vmx_get_feature_msr, + .get_msr = vt_get_msr, + .set_msr = vt_set_msr, + + .get_segment_base = vt_get_segment_base, + .get_segment = vt_get_segment, + .set_segment = vt_set_segment, + .get_cpl = vt_get_cpl, + .get_cpl_no_cache = vt_get_cpl_no_cache, + .get_cs_db_l_bits = vt_get_cs_db_l_bits, + .is_valid_cr0 = vt_is_valid_cr0, + .set_cr0 = vt_set_cr0, + .is_valid_cr4 = vt_is_valid_cr4, + .set_cr4 = vt_set_cr4, + .set_efer = vt_set_efer, + .get_idt = vt_get_idt, + .set_idt = vt_set_idt, + .get_gdt = vt_get_gdt, + .set_gdt = vt_set_gdt, + .set_dr6 = vt_set_dr6, + .set_dr7 = vt_set_dr7, + .sync_dirty_debug_regs = vt_sync_dirty_debug_regs, + .cache_reg = vt_cache_reg, + .get_rflags = vt_get_rflags, + .set_rflags = vt_set_rflags, + .get_if_flag = vt_get_if_flag, + + .flush_tlb_all = vt_flush_tlb_all, + .flush_tlb_current = vt_flush_tlb_current, + .flush_tlb_gva = vt_flush_tlb_gva, + .flush_tlb_guest = vt_flush_tlb_guest, + + .vcpu_pre_run = vt_vcpu_pre_run, + .vcpu_run = vt_vcpu_run, + .handle_exit = vt_handle_exit, + .skip_emulated_instruction = vmx_skip_emulated_instruction, + .update_emulated_instruction = vmx_update_emulated_instruction, + .set_interrupt_shadow = vt_set_interrupt_shadow, + .get_interrupt_shadow = vt_get_interrupt_shadow, + .patch_hypercall = vt_patch_hypercall, + .inject_irq = vt_inject_irq, + .inject_nmi = vt_inject_nmi, + .inject_exception = vt_inject_exception, + .cancel_injection = vt_cancel_injection, + .interrupt_allowed = vt_interrupt_allowed, + .nmi_allowed = vt_nmi_allowed, + .get_nmi_mask = vt_get_nmi_mask, + .set_nmi_mask = vt_set_nmi_mask, + .enable_nmi_window = vt_enable_nmi_window, + .enable_irq_window = vt_enable_irq_window, + .update_cr8_intercept = vt_update_cr8_intercept, + + .x2apic_icr_is_split = false, + .set_virtual_apic_mode = vt_set_virtual_apic_mode, + .set_apic_access_page_addr = vt_set_apic_access_page_addr, + .refresh_apicv_exec_ctrl = vt_refresh_apicv_exec_ctrl, + .load_eoi_exitmap = vt_load_eoi_exitmap, + .apicv_pre_state_restore = vt_apicv_pre_state_restore, + .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, + .hwapic_isr_update = vt_hwapic_isr_update, + .sync_pir_to_irr = vt_sync_pir_to_irr, + .deliver_interrupt = vt_deliver_interrupt, + .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt, + + .set_tss_addr = vt_set_tss_addr, + .set_identity_map_addr = vt_set_identity_map_addr, + .get_mt_mask = vmx_get_mt_mask, + + .get_exit_info = vt_get_exit_info, + .get_entry_info = vt_get_entry_info, + + .vcpu_after_set_cpuid = vt_vcpu_after_set_cpuid, + + .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, + + .get_l2_tsc_offset = vt_get_l2_tsc_offset, + .get_l2_tsc_multiplier = vt_get_l2_tsc_multiplier, + .write_tsc_offset = vt_write_tsc_offset, + .write_tsc_multiplier = vt_write_tsc_multiplier, + + .load_mmu_pgd = vt_load_mmu_pgd, + + .check_intercept = vmx_check_intercept, + .handle_exit_irqoff = vmx_handle_exit_irqoff, + + .update_cpu_dirty_logging = vt_update_cpu_dirty_logging, + + .nested_ops = &vmx_nested_ops, + + .pi_update_irte = vmx_pi_update_irte, + .pi_start_assignment = vmx_pi_start_assignment, + +#ifdef CONFIG_X86_64 + .set_hv_timer = vt_set_hv_timer, + .cancel_hv_timer = vt_cancel_hv_timer, +#endif + + .setup_mce = vt_setup_mce, + +#ifdef CONFIG_KVM_SMM + .smi_allowed = vt_smi_allowed, + .enter_smm = vt_enter_smm, + .leave_smm = vt_leave_smm, + .enable_smi_window = vt_enable_smi_window, +#endif + + .check_emulate_instruction = vt_check_emulate_instruction, + .apic_init_signal_blocked = vt_apic_init_signal_blocked, + .migrate_timers = vmx_migrate_timers, + + .msr_filter_changed = vt_msr_filter_changed, + .complete_emulated_msr = vt_complete_emulated_msr, + + .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, + + .get_untagged_addr = vmx_get_untagged_addr, + + .mem_enc_ioctl = vt_mem_enc_ioctl, + .vcpu_mem_enc_ioctl = vt_vcpu_mem_enc_ioctl, + + .private_max_mapping_level = vt_gmem_private_max_mapping_level +}; + +struct kvm_x86_init_ops vt_init_ops __initdata = { + .hardware_setup = vt_hardware_setup, + .handle_intel_pt_intr = NULL, + + .runtime_ops = &vt_x86_ops, + .pmu_ops = &intel_pmu_ops, +}; + +static void __exit vt_exit(void) +{ + kvm_exit(); + tdx_cleanup(); + vmx_exit(); +} +module_exit(vt_exit); + +static int __init vt_init(void) +{ + unsigned vcpu_size, vcpu_align; + int r; + + r = vmx_init(); + if (r) + return r; + + /* tdx_init() has been taken */ + r = tdx_bringup(); + if (r) + goto err_tdx_bringup; + + /* + * TDX and VMX have different vCPU structures. Calculate the + * maximum size/align so that kvm_init() can use the larger + * values to create the kmem_vcpu_cache. + */ + vcpu_size = sizeof(struct vcpu_vmx); + vcpu_align = __alignof__(struct vcpu_vmx); + if (enable_tdx) { + vcpu_size = max_t(unsigned, vcpu_size, + sizeof(struct vcpu_tdx)); + vcpu_align = max_t(unsigned, vcpu_align, + __alignof__(struct vcpu_tdx)); + kvm_caps.supported_vm_types |= BIT(KVM_X86_TDX_VM); + } + + /* + * Common KVM initialization _must_ come last, after this, /dev/kvm is + * exposed to userspace! + */ + r = kvm_init(vcpu_size, vcpu_align, THIS_MODULE); + if (r) + goto err_kvm_init; + + return 0; + +err_kvm_init: + tdx_cleanup(); +err_tdx_bringup: + vmx_exit(); + return r; +} +module_init(vt_init); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d05ddf751491..71701e2414a4 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -6,16 +6,18 @@ #include <asm/debugreg.h> #include <asm/mmu_context.h> +#include <asm/msr.h> +#include "x86.h" #include "cpuid.h" #include "hyperv.h" #include "mmu.h" #include "nested.h" #include "pmu.h" +#include "posted_intr.h" #include "sgx.h" #include "trace.h" #include "vmx.h" -#include "x86.h" #include "smm.h" static bool __read_mostly enable_shadow_vmcs = 1; @@ -230,11 +232,8 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); - if (nested_vmx_is_evmptr12_valid(vmx)) { - kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true); - vmx->nested.hv_evmcs = NULL; - } - + kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map); + vmx->nested.hv_evmcs = NULL; vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; if (hv_vcpu) { @@ -259,7 +258,7 @@ static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr) * state. It is possible that the area will stay mapped as * vmx->nested.hv_evmcs but this shouldn't be a problem. */ - if (!guest_cpuid_has_evmcs(vcpu) || + if (!guest_cpu_cap_has_evmcs(vcpu) || !evmptr_is_valid(nested_get_evmptr(vcpu))) return false; @@ -277,7 +276,7 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, { struct vmcs_host_state *dest, *src; - if (unlikely(!vmx->guest_state_loaded)) + if (unlikely(!vmx->vt.guest_state_loaded)) return; src = &prev->host_state; @@ -316,6 +315,16 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) vcpu->arch.regs_dirty = 0; } +static void nested_put_vmcs12_pages(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map); + kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map); + kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map); + vmx->nested.pi_desc = NULL; +} + /* * Free whatever needs to be freed from vmx->nested when L1 goes down, or * just stops using VMX. @@ -348,15 +357,8 @@ static void free_nested(struct kvm_vcpu *vcpu) vmx->nested.cached_vmcs12 = NULL; kfree(vmx->nested.cached_shadow_vmcs12); vmx->nested.cached_shadow_vmcs12 = NULL; - /* - * Unpin physical memory we referred to in the vmcs02. The APIC access - * page's backing page (yeah, confusing) shouldn't actually be accessed, - * and if it is written, the contents are irrelevant. - */ - kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map, false); - kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true); - kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true); - vmx->nested.pi_desc = NULL; + + nested_put_vmcs12_pages(vcpu); kvm_mmu_free_roots(vcpu->kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL); @@ -409,18 +411,40 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long exit_qualification; u32 vm_exit_reason; - unsigned long exit_qualification = vcpu->arch.exit_qualification; if (vmx->nested.pml_full) { vm_exit_reason = EXIT_REASON_PML_FULL; vmx->nested.pml_full = false; - exit_qualification &= INTR_INFO_UNBLOCK_NMI; + + /* + * It should be impossible to trigger a nested PML Full VM-Exit + * for anything other than an EPT Violation from L2. KVM *can* + * trigger nEPT page fault injection in response to an EPT + * Misconfig, e.g. if the MMIO SPTE was stale and L1's EPT + * tables also changed, but KVM should not treat EPT Misconfig + * VM-Exits as writes. + */ + WARN_ON_ONCE(vmx->vt.exit_reason.basic != EXIT_REASON_EPT_VIOLATION); + + /* + * PML Full and EPT Violation VM-Exits both use bit 12 to report + * "NMI unblocking due to IRET", i.e. the bit can be propagated + * as-is from the original EXIT_QUALIFICATION. + */ + exit_qualification = vmx_get_exit_qual(vcpu) & INTR_INFO_UNBLOCK_NMI; } else { - if (fault->error_code & PFERR_RSVD_MASK) + if (fault->error_code & PFERR_RSVD_MASK) { vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; - else + exit_qualification = 0; + } else { + exit_qualification = fault->exit_qualification; + exit_qualification |= vmx_get_exit_qual(vcpu) & + (EPT_VIOLATION_GVA_IS_VALID | + EPT_VIOLATION_GVA_TRANSLATED); vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + } /* * Although the caller (kvm_inject_emulated_page_fault) would @@ -601,7 +625,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, int msr; unsigned long *msr_bitmap_l1; unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; - struct kvm_host_map *map = &vmx->nested.msr_bitmap_map; + struct kvm_host_map map; /* Nothing to do if the MSR bitmap is not in use. */ if (!cpu_has_vmx_msr_bitmap() || @@ -624,10 +648,10 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, return true; } - if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map)) + if (kvm_vcpu_map_readonly(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), &map)) return false; - msr_bitmap_l1 = (unsigned long *)map->hva; + msr_bitmap_l1 = (unsigned long *)map.hva; /* * To keep the control flow simple, pay eight 8-byte writes (sixteen @@ -691,7 +715,7 @@ 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_FLUSH_CMD, MSR_TYPE_W); - kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); + kvm_vcpu_unmap(vcpu, &map); vmx->nested.force_msr_bitmap_recalc = false; @@ -958,7 +982,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) __func__, i, e.index, e.reserved); goto fail; } - if (kvm_set_msr(vcpu, e.index, e.value)) { + if (kvm_set_msr_with_filter(vcpu, e.index, e.value)) { pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", __func__, i, e.index, e.value); @@ -994,7 +1018,7 @@ static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu, } } - if (kvm_get_msr(vcpu, msr_index, data)) { + if (kvm_get_msr_with_filter(vcpu, msr_index, data)) { pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__, msr_index); return false; @@ -1089,9 +1113,9 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, /* * Emulated VMEntry does not fail here. Instead a less * accurate value will be returned by - * nested_vmx_get_vmexit_msr_value() using kvm_get_msr() - * instead of reading the value from the vmcs02 VMExit - * MSR-store area. + * nested_vmx_get_vmexit_msr_value() by reading KVM's + * internal MSR state instead of reading the value from + * the vmcs02 VMExit MSR-store area. */ pr_warn_ratelimited( "Not enough msr entries in msr_autostore. Can't add msr %x\n", @@ -1174,11 +1198,14 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, kvm_hv_nested_transtion_tlb_flush(vcpu, enable_ept); /* - * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings - * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a - * full TLB flush from the guest's perspective. This is required even - * if VPID is disabled in the host as KVM may need to synchronize the - * MMU in response to the guest TLB flush. + * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the + * same VPID as the host, and so architecturally, linear and combined + * mappings for VPID=0 must be flushed at VM-Enter and VM-Exit. KVM + * emulates L2 sharing L1's VPID=0 by using vpid01 while running L2, + * and so KVM must also emulate TLB flush of VPID=0, i.e. vpid01. This + * is required if VPID is disabled in KVM, as a TLB flush (there are no + * VPIDs) still occurs from L1's perspective, and KVM may need to + * synchronize the MMU in response to the guest TLB flush. * * Note, using TLB_FLUSH_GUEST is correct even if nested EPT is in use. * EPT is a special snowflake, as guest-physical mappings aren't @@ -1228,21 +1255,32 @@ static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data) { - const u64 feature_and_reserved = - /* feature (except bit 48; see below) */ - BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) | - /* reserved */ - BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56); + const u64 feature_bits = VMX_BASIC_DUAL_MONITOR_TREATMENT | + VMX_BASIC_INOUT | + VMX_BASIC_TRUE_CTLS; + + const u64 reserved_bits = GENMASK_ULL(63, 56) | + GENMASK_ULL(47, 45) | + BIT_ULL(31); + u64 vmx_basic = vmcs_config.nested.basic; - if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved)) + BUILD_BUG_ON(feature_bits & reserved_bits); + + /* + * Except for 32BIT_PHYS_ADDR_ONLY, which is an anti-feature bit (has + * inverted polarity), the incoming value must not set feature bits or + * reserved bits that aren't allowed/supported by KVM. Fields, i.e. + * multi-bit values, are explicitly checked below. + */ + if (!is_bitwise_subset(vmx_basic, data, feature_bits | reserved_bits)) return -EINVAL; /* * KVM does not emulate a version of VMX that constrains physical * addresses of VMX structures (e.g. VMCS) to 32-bits. */ - if (data & BIT_ULL(48)) + if (data & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EINVAL; if (vmx_basic_vmcs_revision_id(vmx_basic) != @@ -1311,16 +1349,29 @@ vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data) { - const u64 feature_and_reserved_bits = - /* feature */ - BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) | - BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) | - /* reserved */ - GENMASK_ULL(13, 9) | BIT_ULL(31); + const u64 feature_bits = VMX_MISC_SAVE_EFER_LMA | + VMX_MISC_ACTIVITY_HLT | + VMX_MISC_ACTIVITY_SHUTDOWN | + VMX_MISC_ACTIVITY_WAIT_SIPI | + VMX_MISC_INTEL_PT | + VMX_MISC_RDMSR_IN_SMM | + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | + VMX_MISC_VMXOFF_BLOCK_SMI | + VMX_MISC_ZERO_LEN_INS; + + const u64 reserved_bits = BIT_ULL(31) | GENMASK_ULL(13, 9); + u64 vmx_misc = vmx_control_msr(vmcs_config.nested.misc_low, vmcs_config.nested.misc_high); - if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits)) + BUILD_BUG_ON(feature_bits & reserved_bits); + + /* + * The incoming value must not set feature bits or reserved bits that + * aren't allowed/supported by KVM. Fields, i.e. multi-bit values, are + * explicitly checked below. + */ + if (!is_bitwise_subset(vmx_misc, data, feature_bits | reserved_bits)) return -EINVAL; if ((vmx->nested.msrs.pinbased_ctls_high & @@ -2039,7 +2090,7 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( bool evmcs_gpa_changed = false; u64 evmcs_gpa; - if (likely(!guest_cpuid_has_evmcs(vcpu))) + if (likely(!guest_cpu_cap_has_evmcs(vcpu))) return EVMPTRLD_DISABLED; evmcs_gpa = nested_get_evmptr(vcpu); @@ -2220,6 +2271,9 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) vmcs_write64(EPT_POINTER, construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL)); + if (vmx->ve_info) + vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info)); + /* All VMFUNCs are currently emulated through L0 vmexits. */ if (cpu_has_vmx_vmfunc()) vmcs_write64(VM_FUNCTION_CONTROL, 0); @@ -2265,6 +2319,17 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA); + /* + * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the + * same VPID as the host. Emulate this behavior by using vpid01 for L2 + * if VPID is disabled in vmcs12. Note, if VPID is disabled, VM-Enter + * and VM-Exit are architecturally required to flush VPID=0, but *only* + * VPID=0. I.e. using vpid02 would be ok (so long as KVM emulates the + * required flushes), but doing so would cause KVM to over-flush. E.g. + * if L1 runs L2 X with VPID12=1, then runs L2 Y with VPID12 disabled, + * and then runs L2 X again, then KVM can and should retain TLB entries + * for VPID12=1. + */ if (enable_vpid) { if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02); @@ -2291,10 +2356,12 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 /* Posted interrupts setting is only taken from vmcs12. */ vmx->nested.pi_pending = false; - if (nested_cpu_has_posted_intr(vmcs12)) + if (nested_cpu_has_posted_intr(vmcs12)) { vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; - else + } else { + vmx->nested.posted_intr_nv = -1; exec_control &= ~PIN_BASED_POSTED_INTR; + } pin_controls_set(vmx, exec_control); /* @@ -2400,7 +2467,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 if (cpu_has_load_ia32_efer()) { if (guest_efer & EFER_LMA) exec_control |= VM_ENTRY_IA32E_MODE; - if (guest_efer != host_efer) + if (guest_efer != kvm_host.efer) exec_control |= VM_ENTRY_LOAD_IA32_EFER; } vm_entry_controls_set(vmx, exec_control); @@ -2413,7 +2480,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 * bits may be modified by vmx_set_efer() in prepare_vmcs02(). */ exec_control = __vm_exit_controls_get(vmcs01); - if (cpu_has_load_ia32_efer() && guest_efer != host_efer) + if (cpu_has_load_ia32_efer() && guest_efer != kvm_host.efer) exec_control |= VM_EXIT_LOAD_IA32_EFER; else exec_control &= ~VM_EXIT_LOAD_IA32_EFER; @@ -2444,6 +2511,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) { + vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector); vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector); @@ -2481,7 +2549,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); - vmx->segment_cache.bitmask = 0; + vmx_segment_cache_clear(vmx); } if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & @@ -2903,7 +2971,7 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, case INTR_TYPE_SOFT_EXCEPTION: case INTR_TYPE_SOFT_INTR: case INTR_TYPE_PRIV_SW_EXCEPTION: - if (CC(vmcs12->vm_entry_instruction_len > 15) || + if (CC(vmcs12->vm_entry_instruction_len > X86_MAX_INSTRUCTION_LENGTH) || CC(vmcs12->vm_entry_instruction_len == 0 && CC(!nested_cpu_has_zero_length_injection(vcpu)))) return -EINVAL; @@ -2925,7 +2993,7 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, return -EINVAL; #ifdef CONFIG_KVM_HYPERV - if (guest_cpuid_has_evmcs(vcpu)) + if (guest_cpu_cap_has_evmcs(vcpu)) return nested_evmcs_check_controls(vmcs12); #endif @@ -2943,6 +3011,17 @@ static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu, return 0; } +static bool is_l1_noncanonical_address_on_vmexit(u64 la, struct vmcs12 *vmcs12) +{ + /* + * Check that the given linear address is canonical after a VM exit + * from L2, based on HOST_CR4.LA57 value that will be loaded for L1. + */ + u8 l1_address_bits_on_exit = (vmcs12->host_cr4 & X86_CR4_LA57) ? 57 : 48; + + return !__is_canonical_address(la, l1_address_bits_on_exit); +} + static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -2953,8 +3032,8 @@ 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(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu))) + 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; if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) && @@ -2988,12 +3067,12 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, CC(vmcs12->host_ss_selector == 0 && !ia32e)) return -EINVAL; - if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_idtr_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_rip, vcpu))) + if (CC(is_noncanonical_base_address(vmcs12->host_fs_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_gs_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_gdtr_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_idtr_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_tr_base, vcpu)) || + CC(is_l1_noncanonical_address_on_vmexit(vmcs12->host_rip, vmcs12))) return -EINVAL; /* @@ -3111,7 +3190,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) && - (CC(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) || + (CC(is_noncanonical_msr_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) || CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))) return -EINVAL; @@ -3209,7 +3288,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) * L2 was running), map it here to make sure vmcs12 changes are * properly reflected. */ - if (guest_cpuid_has_evmcs(vcpu) && + if (guest_cpu_cap_has_evmcs(vcpu) && vmx->nested.hv_evmcs_vmptr == EVMPTR_MAP_PENDING) { enum nested_evmptrld_status evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, false); @@ -3364,7 +3443,7 @@ static int nested_vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa) if (!nested_cpu_has_pml(vmcs12)) return 0; - if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) { + if (vmcs12->guest_pml_index >= PML_LOG_NR_ENTRIES) { vmx->nested.pml_full = true; return 1; } @@ -3403,14 +3482,6 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) return 1; } -static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu) -{ - u8 rvi = vmx_get_rvi(); - u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI); - - return ((rvi & 0xf0) > (vppr & 0xf0)); -} - static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12); @@ -3430,7 +3501,6 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); enum vm_entry_failure_code entry_failure_code; - bool evaluate_pending_interrupts; union vmx_exit_reason exit_reason = { .basic = EXIT_REASON_INVALID_STATE, .failed_vmentry = 1, @@ -3449,13 +3519,6 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, kvm_service_local_tlb_flush_requests(vcpu); - evaluate_pending_interrupts = exec_controls_get(vmx) & - (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); - if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) - evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); - if (!evaluate_pending_interrupts) - evaluate_pending_interrupts |= kvm_apic_has_pending_init_or_sipi(vcpu); - if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); @@ -3538,9 +3601,13 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, * Re-evaluate pending events if L1 had a pending IRQ/NMI/INIT/SIPI * when it executed VMLAUNCH/VMRESUME, as entering non-root mode can * effectively unblock various events, e.g. INIT/SIPI cause VM-Exit - * unconditionally. + * unconditionally. Take care to pull data from vmcs01 as appropriate, + * e.g. when checking for interrupt windows, as vmcs02 is now loaded. */ - if (unlikely(evaluate_pending_interrupts)) + if ((__exec_controls_get(&vmx->vmcs01) & (CPU_BASED_INTR_WINDOW_EXITING | + CPU_BASED_NMI_WINDOW_EXITING)) || + kvm_apic_has_pending_init_or_sipi(vcpu) || + kvm_apic_has_interrupt(vcpu)) kvm_make_request(KVM_REQ_EVENT, vcpu); /* @@ -3673,14 +3740,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (unlikely(status != NVMX_VMENTRY_SUCCESS)) goto vmentry_failed; - /* Emulate processing of posted interrupts on VM-Enter. */ - if (nested_cpu_has_posted_intr(vmcs12) && - kvm_apic_has_interrupt(vcpu) == vmx->nested.posted_intr_nv) { - vmx->nested.pi_pending = true; - kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_apic_clear_irr(vcpu, vmx->nested.posted_intr_nv); - } - /* Hide L1D cache contents from the nested guest. */ vmx->vcpu.arch.l1tf_flush_l1d = true; @@ -3713,7 +3772,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) break; case GUEST_ACTIVITY_WAIT_SIPI: vmx->nested.nested_run_pending = 0; - vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; + kvm_set_mp_state(vcpu, KVM_MP_STATE_INIT_RECEIVED); break; default: break; @@ -3874,8 +3933,8 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) if (!pi_test_and_clear_on(vmx->nested.pi_desc)) return 0; - max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); - if (max_irr != 256) { + max_irr = pi_find_highest_vector(vmx->nested.pi_desc); + if (max_irr > 0) { vapic_page = vmx->nested.virtual_apic_map.hva; if (!vapic_page) goto mmio_needed; @@ -4006,10 +4065,46 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) to_vmx(vcpu)->nested.preemption_timer_expired; } -static bool vmx_has_nested_events(struct kvm_vcpu *vcpu) +static bool vmx_has_nested_events(struct kvm_vcpu *vcpu, bool for_injection) { - return nested_vmx_preemption_timer_pending(vcpu) || - to_vmx(vcpu)->nested.mtf_pending; + struct vcpu_vmx *vmx = to_vmx(vcpu); + void *vapic = vmx->nested.virtual_apic_map.hva; + int max_irr, vppr; + + if (nested_vmx_preemption_timer_pending(vcpu) || + vmx->nested.mtf_pending) + return true; + + /* + * Virtual Interrupt Delivery doesn't require manual injection. Either + * the interrupt is already in GUEST_RVI and will be recognized by CPU + * at VM-Entry, or there is a KVM_REQ_EVENT pending and KVM will move + * the interrupt from the PIR to RVI prior to entering the guest. + */ + if (for_injection) + return false; + + if (!nested_cpu_has_vid(get_vmcs12(vcpu)) || + __vmx_interrupt_blocked(vcpu)) + return false; + + if (!vapic) + return false; + + vppr = *((u32 *)(vapic + APIC_PROCPRI)); + + max_irr = vmx_get_rvi(); + if ((max_irr & 0xf0) > (vppr & 0xf0)) + return true; + + if (vmx->nested.pi_pending && vmx->nested.pi_desc && + pi_test_on(vmx->nested.pi_desc)) { + max_irr = pi_find_highest_vector(vmx->nested.pi_desc); + if (max_irr > 0 && (max_irr & 0xf0) > (vppr & 0xf0)) + return true; + } + + return false; } /* @@ -4106,13 +4201,25 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) */ bool block_nested_exceptions = vmx->nested.nested_run_pending; /* - * New events (not exceptions) are only recognized at instruction + * Events that don't require injection, i.e. that are virtualized by + * hardware, aren't blocked by a pending VM-Enter as KVM doesn't need + * to regain control in order to deliver the event, and hardware will + * handle event ordering, e.g. with respect to injected exceptions. + * + * But, new events (not exceptions) are only recognized at instruction * boundaries. If an event needs reinjection, then KVM is handling a - * VM-Exit that occurred _during_ instruction execution; new events are - * blocked until the instruction completes. + * VM-Exit that occurred _during_ instruction execution; new events, + * irrespective of whether or not they're injected, are blocked until + * the instruction completes. + */ + bool block_non_injected_events = kvm_event_needs_reinjection(vcpu); + /* + * Inject events are blocked by nested VM-Enter, as KVM is responsible + * for managing priority between concurrent events, i.e. KVM needs to + * wait until after VM-Enter completes to deliver injected events. */ bool block_nested_events = block_nested_exceptions || - kvm_event_needs_reinjection(vcpu); + block_non_injected_events; if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { @@ -4222,11 +4329,71 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) } if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) { + int irq; + + if (!nested_exit_on_intr(vcpu)) { + if (block_nested_events) + return -EBUSY; + + goto no_vmexit; + } + + if (!nested_exit_intr_ack_set(vcpu)) { + if (block_nested_events) + return -EBUSY; + + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); + return 0; + } + + irq = kvm_cpu_get_extint(vcpu); + if (irq != -1) { + if (block_nested_events) + return -EBUSY; + + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); + return 0; + } + + irq = kvm_apic_has_interrupt(vcpu); + if (WARN_ON_ONCE(irq < 0)) + goto no_vmexit; + + /* + * If the IRQ is L2's PI notification vector, process posted + * interrupts for L2 instead of injecting VM-Exit, as the + * detection/morphing architecturally occurs when the IRQ is + * delivered to the CPU. Note, only interrupts that are routed + * through the local APIC trigger posted interrupt processing, + * and enabling posted interrupts requires ACK-on-exit. + */ + if (irq == vmx->nested.posted_intr_nv) { + /* + * Nested posted interrupts are delivered via RVI, i.e. + * aren't injected by KVM, and so can be queued even if + * manual event injection is disallowed. + */ + if (block_non_injected_events) + return -EBUSY; + + vmx->nested.pi_pending = true; + kvm_apic_clear_irr(vcpu, irq); + goto no_vmexit; + } + if (block_nested_events) return -EBUSY; - if (!nested_exit_on_intr(vcpu)) - goto no_vmexit; - nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); + + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); + + /* + * ACK the interrupt _after_ emulating VM-Exit, as the IRQ must + * be marked as in-service in vmcs01.GUEST_INTERRUPT_STATUS.SVI + * if APICv is active. + */ + kvm_apic_ack_interrupt(vcpu, irq); return 0; } @@ -4452,11 +4619,11 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) */ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, u32 vm_exit_reason, u32 exit_intr_info, - unsigned long exit_qualification) + unsigned long exit_qualification, u32 exit_insn_len) { /* update exit information fields: */ vmcs12->vm_exit_reason = vm_exit_reason; - if (to_vmx(vcpu)->exit_reason.enclave_mode) + if (vmx_get_exit_reason(vcpu).enclave_mode) vmcs12->vm_exit_reason |= VMX_EXIT_REASONS_SGX_ENCLAVE_MODE; vmcs12->exit_qualification = exit_qualification; @@ -4480,7 +4647,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vm_exit_reason, exit_intr_info); vmcs12->vm_exit_intr_info = exit_intr_info; - vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); + vmcs12->vm_exit_instruction_len = exit_insn_len; vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); /* @@ -4628,7 +4795,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmcs12->vm_exit_msr_load_count)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); - to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); + to_vt(vcpu)->emulation_required = vmx_emulation_required(vcpu); } static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) @@ -4640,7 +4807,7 @@ static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) return vmcs_read64(GUEST_IA32_EFER); if (cpu_has_load_ia32_efer()) - return host_efer; + return kvm_host.efer; for (i = 0; i < vmx->msr_autoload.guest.nr; ++i) { if (vmx->msr_autoload.guest.val[i].index == MSR_EFER) @@ -4651,7 +4818,7 @@ static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) if (efer_msr) return efer_msr->data; - return host_efer; + return kvm_host.efer; } static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) @@ -4744,7 +4911,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) goto vmabort; } - if (kvm_set_msr(vcpu, h.index, h.value)) { + if (kvm_set_msr_with_filter(vcpu, h.index, h.value)) { pr_debug_ratelimited( "%s WRMSR failed (%u, 0x%x, 0x%llx)\n", __func__, j, h.index, h.value); @@ -4764,8 +4931,9 @@ vmabort: * and modify vmcs12 to make it see what it would expect to see there if * L2 was its real guest. Must only be called when in L2 (is_guest_mode()) */ -void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, - u32 exit_intr_info, unsigned long exit_qualification) +void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, + u32 exit_intr_info, unsigned long exit_qualification, + u32 exit_insn_len) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); @@ -4815,7 +4983,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, if (vm_exit_reason != -1) prepare_vmcs12(vcpu, vmcs12, vm_exit_reason, - exit_intr_info, exit_qualification); + exit_intr_info, exit_qualification, + exit_insn_len); /* * Must happen outside of sync_vmcs02_to_vmcs12() as it will @@ -4860,7 +5029,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, * doesn't isolate different VMCSs, i.e. in this case, doesn't provide * separate modes for L2 vs L1. */ - if (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL)) indirect_branch_prediction_barrier(); /* Update any VMCS fields that might have changed while L2 ran */ @@ -4883,11 +5052,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vmx_update_cpu_dirty_logging(vcpu); } - /* Unpin physical memory we referred to in vmcs02 */ - kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map, false); - kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true); - kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true); - vmx->nested.pi_desc = NULL; + nested_put_vmcs12_pages(vcpu); if (vmx->nested.reload_vmcs01_apic_access_page) { vmx->nested.reload_vmcs01_apic_access_page = false; @@ -4899,22 +5064,19 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); } + if (vmx->nested.update_vmcs01_hwapic_isr) { + vmx->nested.update_vmcs01_hwapic_isr = false; + kvm_apic_update_hwapic_isr(vcpu); + } + if ((vm_exit_reason != -1) && (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))) vmx->nested.need_vmcs12_to_shadow_sync = true; /* in case we halted in L2 */ - vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); if (likely(!vmx->fail)) { - if ((u16)vm_exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && - nested_exit_intr_ack_set(vcpu)) { - int irq = kvm_cpu_get_interrupt(vcpu); - WARN_ON(irq < 0); - vmcs12->vm_exit_intr_info = irq | - INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR; - } - if (vm_exit_reason != -1) trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, vmcs12->exit_qualification, @@ -4925,6 +5087,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, load_vmcs12_host_state(vcpu, vmcs12); + /* + * Process events if an injectable IRQ or NMI is pending, even + * if the event is blocked (RFLAGS.IF is cleared on VM-Exit). + * If an event became pending while L2 was active, KVM needs to + * either inject the event or request an IRQ/NMI window. SMIs + * don't need to be processed as SMM is mutually exclusive with + * non-root mode. INIT/SIPI don't need to be checked as INIT + * is blocked post-VMXON, and SIPIs are ignored. + */ + if (kvm_cpu_has_injectable_intr(vcpu) || vcpu->arch.nmi_pending) + kvm_make_request(KVM_REQ_EVENT, vcpu); return; } @@ -5031,7 +5204,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, * non-canonical form. This is the only check on the memory * destination for long mode! */ - exn = is_noncanonical_address(*ret, vcpu); + exn = is_noncanonical_address(*ret, vcpu, 0); } else { /* * When not in long mode, the virtual/linear address is @@ -5157,9 +5330,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) if (enable_shadow_vmcs && !alloc_shadow_vmcs(vcpu)) goto out_shadow_vmcs; - hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS_PINNED); - vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; + hrtimer_setup(&vmx->nested.preemption_timer, vmx_preemption_timer_fn, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED); vmx->nested.vpid02 = allocate_vpid(); @@ -5828,6 +6000,12 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + /* + * Always flush the effective vpid02, i.e. never flush the current VPID + * and never explicitly flush vpid01. INVVPID targets a VPID, not a + * VMCS, and so whether or not the current vmcs12 has VPID enabled is + * irrelevant (and there may not be a loaded vmcs12). + */ vpid02 = nested_get_vpid02(vcpu); switch (type) { case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: @@ -5836,7 +6014,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) * invalidation. */ if (!operand.vpid || - is_noncanonical_address(operand.gla, vcpu)) + is_noncanonical_invlpg_address(operand.gla, vcpu)) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); vpid_sync_vcpu_addr(vpid02, operand.gla); @@ -5950,7 +6128,7 @@ fail: * nested VM-Exit. Pass the original exit reason, i.e. don't hardcode * EXIT_REASON_VMFUNC as the exit reason. */ - nested_vmx_vmexit(vcpu, vmx->exit_reason.full, + nested_vmx_vmexit(vcpu, vmx->vt.exit_reason.full, vmx_get_intr_info(vcpu), vmx_get_exit_qual(vcpu)); return 1; @@ -6130,7 +6308,7 @@ static bool nested_vmx_exit_handled_encls(struct kvm_vcpu *vcpu, { u32 encls_leaf; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SGX) || + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SGX) || !nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENCLS_EXITING)) return false; @@ -6208,6 +6386,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, else if (is_alignment_check(intr_info) && !vmx_guest_inject_ac(vcpu)) return true; + else if (is_ve_fault(intr_info)) + return true; return false; case EXIT_REASON_EXTERNAL_INTERRUPT: return true; @@ -6393,7 +6573,7 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - union vmx_exit_reason exit_reason = vmx->exit_reason; + union vmx_exit_reason exit_reason = vmx->vt.exit_reason; unsigned long exit_qual; u32 exit_intr_info; @@ -6466,7 +6646,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, vmx = to_vmx(vcpu); vmcs12 = get_vmcs12(vcpu); - if (guest_can_use(vcpu, X86_FEATURE_VMX) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX) && (vmx->nested.vmxon || vmx->nested.smm.vmxon)) { kvm_state.hdr.vmx.vmxon_pa = vmx->nested.vmxon_ptr; kvm_state.hdr.vmx.vmcs12_pa = vmx->nested.current_vmptr; @@ -6607,7 +6787,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS) return -EINVAL; } else { - if (!guest_can_use(vcpu, X86_FEATURE_VMX)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return -EINVAL; if (!page_address_valid(vcpu, kvm_state->hdr.vmx.vmxon_pa)) @@ -6641,7 +6821,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) && - (!guest_can_use(vcpu, X86_FEATURE_VMX) || + (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX) || !vmx->nested.enlightened_vmcs_enabled)) return -EINVAL; @@ -6987,7 +7167,7 @@ static void nested_vmx_setup_misc_data(struct vmcs_config *vmcs_conf, { msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA; msrs->misc_low |= - MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE | VMX_MISC_ACTIVITY_HLT | VMX_MISC_ACTIVITY_WAIT_SIPI; @@ -7002,12 +7182,10 @@ static void nested_vmx_setup_basic(struct nested_vmx_msrs *msrs) * guest, and the VMCS structure we give it - not about the * VMX support of the underlying hardware. */ - msrs->basic = - VMCS12_REVISION | - VMX_BASIC_TRUE_CTLS | - ((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) | - (VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT); + msrs->basic = vmx_basic_encode_vmcs_info(VMCS12_REVISION, VMCS12_SIZE, + X86_MEMTYPE_WB); + msrs->basic |= VMX_BASIC_TRUE_CTLS; if (cpu_has_vmx_basic_inout()) msrs->basic |= VMX_BASIC_INOUT; } @@ -7025,8 +7203,8 @@ static void nested_vmx_setup_cr_fixed(struct nested_vmx_msrs *msrs) msrs->cr4_fixed0 = VMXON_CR4_ALWAYSON; /* These MSRs specify bits which the guest must keep fixed off. */ - rdmsrl(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1); - rdmsrl(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1); + rdmsrq(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1); + rdmsrq(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1); if (vmx_umip_emulated()) msrs->cr4_fixed1 |= X86_CR4_UMIP; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index cce4e2aa30fb..6eedcfc91070 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -26,8 +26,26 @@ void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu); enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry); bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu); -void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, - u32 exit_intr_info, unsigned long exit_qualification); +void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, + u32 exit_intr_info, unsigned long exit_qualification, + u32 exit_insn_len); + +static inline void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, + u32 exit_intr_info, + unsigned long exit_qualification) +{ + u32 exit_insn_len; + + if (to_vmx(vcpu)->fail || vm_exit_reason == -1 || + (vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) + exit_insn_len = 0; + else + exit_insn_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); + + __nested_vmx_vmexit(vcpu, vm_exit_reason, exit_intr_info, + exit_qualification, exit_insn_len); +} + void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu); int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata); @@ -39,11 +57,17 @@ bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { + lockdep_assert_once(lockdep_is_held(&vcpu->mutex) || + !refcount_read(&vcpu->kvm->users_count)); + return to_vmx(vcpu)->nested.cached_vmcs12; } static inline struct vmcs12 *get_shadow_vmcs12(struct kvm_vcpu *vcpu) { + lockdep_assert_once(lockdep_is_held(&vcpu->mutex) || + !refcount_read(&vcpu->kvm->users_count)); + return to_vmx(vcpu)->nested.cached_shadow_vmcs12; } @@ -109,7 +133,7 @@ static inline unsigned nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu) static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu) { return to_vmx(vcpu)->nested.msrs.misc_low & - MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS; + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS; } static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index be40474de6e4..bbf4509f32d0 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -13,12 +13,14 @@ #include <linux/types.h> #include <linux/kvm_host.h> #include <linux/perf_event.h> +#include <asm/msr.h> #include <asm/perf_event.h> #include "x86.h" #include "cpuid.h" #include "lapic.h" #include "nested.h" #include "pmu.h" +#include "tdx.h" /* * Perf's "BASE" is wildly misleading, architectural PMUs use bits 31:16 of ECX @@ -34,6 +36,24 @@ #define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0) +static struct lbr_desc *vcpu_to_lbr_desc(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return NULL; + + return &to_vmx(vcpu)->lbr_desc; +} + +static struct x86_pmu_lbr *vcpu_to_lbr_records(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return NULL; + + return &to_vmx(vcpu)->lbr_desc.records; +} + +#pragma GCC poison to_vmx + static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) { struct kvm_pmc *pmc; @@ -110,7 +130,7 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, static inline u64 vcpu_get_perf_capabilities(struct kvm_vcpu *vcpu) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM)) return 0; return vcpu->arch.perf_capabilities; @@ -129,6 +149,22 @@ static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr) return get_gp_pmc(pmu, msr, MSR_IA32_PMC0); } +static bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return false; + + return cpuid_model_is_consistent(vcpu); +} + +bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu) +{ + if (is_td_vcpu(vcpu)) + return false; + + return !!vcpu_to_lbr_records(vcpu)->nr; +} + static bool intel_pmu_is_valid_lbr_msr(struct kvm_vcpu *vcpu, u32 index) { struct x86_pmu_lbr *records = vcpu_to_lbr_records(vcpu); @@ -160,7 +196,7 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) ret = vcpu_get_perf_capabilities(vcpu) & PERF_CAP_PEBS_FORMAT; break; case MSR_IA32_DS_AREA: - ret = guest_cpuid_has(vcpu, X86_FEATURE_DS); + ret = guest_cpu_cap_has(vcpu, X86_FEATURE_DS); break; case MSR_PEBS_DATA_CFG: perf_capabilities = vcpu_get_perf_capabilities(vcpu); @@ -194,6 +230,9 @@ static inline void intel_pmu_release_guest_lbr_event(struct kvm_vcpu *vcpu) { struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + if (!lbr_desc) + return; + if (lbr_desc->event) { perf_event_release_kernel(lbr_desc->event); lbr_desc->event = NULL; @@ -235,6 +274,9 @@ int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu) PERF_SAMPLE_BRANCH_USER, }; + if (WARN_ON_ONCE(!lbr_desc)) + return 0; + if (unlikely(lbr_desc->event)) { __set_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use); return 0; @@ -279,9 +321,9 @@ static bool intel_pmu_handle_lbr_msrs_access(struct kvm_vcpu *vcpu, local_irq_disable(); if (lbr_desc->event->state == PERF_EVENT_STATE_ACTIVE) { if (read) - rdmsrl(index, msr_info->data); + rdmsrq(index, msr_info->data); else - wrmsrl(index, msr_info->data); + wrmsrq(index, msr_info->data); __set_bit(INTEL_PMC_IDX_FIXED_VLBR, vcpu_to_pmu(vcpu)->pmc_in_use); local_irq_enable(); return true; @@ -348,14 +390,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr) { case MSR_CORE_PERF_FIXED_CTR_CTRL: - if (data & pmu->fixed_ctr_ctrl_mask) + if (data & pmu->fixed_ctr_ctrl_rsvd) return 1; if (pmu->fixed_ctr_ctrl != data) reprogram_fixed_counters(pmu, data); break; case MSR_IA32_PEBS_ENABLE: - if (data & pmu->pebs_enable_mask) + if (data & pmu->pebs_enable_rsvd) return 1; if (pmu->pebs_enable != data) { @@ -365,13 +407,13 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } break; case MSR_IA32_DS_AREA: - if (is_noncanonical_address(data, vcpu)) + if (is_noncanonical_msr_address(data, vcpu)) return 1; pmu->ds_area = data; break; case MSR_PEBS_DATA_CFG: - if (data & pmu->pebs_data_cfg_mask) + if (data & pmu->pebs_data_cfg_rsvd) return 1; pmu->pebs_data_cfg = data; @@ -436,8 +478,8 @@ static __always_inline u64 intel_get_fixed_pmc_eventsel(unsigned int index) }; u64 eventsel; - BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_perf_ids) != KVM_PMC_MAX_FIXED); - BUILD_BUG_ON(index >= KVM_PMC_MAX_FIXED); + BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_perf_ids) != KVM_MAX_NR_INTEL_FIXED_COUTNERS); + BUILD_BUG_ON(index >= KVM_MAX_NR_INTEL_FIXED_COUTNERS); /* * Yell if perf reports support for a fixed counter but perf doesn't @@ -448,6 +490,14 @@ static __always_inline u64 intel_get_fixed_pmc_eventsel(unsigned int index) return eventsel; } +static void intel_pmu_enable_fixed_counter_bits(struct kvm_pmu *pmu, u64 bits) +{ + int i; + + for (i = 0; i < pmu->nr_arch_fixed_counters; i++) + pmu->fixed_ctr_ctrl_rsvd &= ~intel_fixed_bits_by_idx(i, bits); +} + static void intel_pmu_refresh(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -456,8 +506,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) union cpuid10_eax eax; union cpuid10_edx edx; u64 perf_capabilities; - u64 counter_mask; - int i; + u64 counter_rsvd; + + if (!lbr_desc) + return; memset(&lbr_desc->records, 0, sizeof(lbr_desc->records)); @@ -501,22 +553,24 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) ((u64)1 << edx.split.bit_width_fixed) - 1; } - for (i = 0; i < pmu->nr_arch_fixed_counters; i++) - pmu->fixed_ctr_ctrl_mask &= ~(0xbull << (i * 4)); - counter_mask = ~(((1ull << pmu->nr_arch_gp_counters) - 1) | + intel_pmu_enable_fixed_counter_bits(pmu, INTEL_FIXED_0_KERNEL | + INTEL_FIXED_0_USER | + INTEL_FIXED_0_ENABLE_PMI); + + counter_rsvd = ~(((1ull << pmu->nr_arch_gp_counters) - 1) | (((1ull << pmu->nr_arch_fixed_counters) - 1) << KVM_FIXED_PMC_BASE_IDX)); - pmu->global_ctrl_mask = counter_mask; + pmu->global_ctrl_rsvd = counter_rsvd; /* * GLOBAL_STATUS and GLOBAL_OVF_CONTROL (a.k.a. GLOBAL_STATUS_RESET) * share reserved bit definitions. The kernel just happens to use * OVF_CTRL for the names. */ - pmu->global_status_mask = pmu->global_ctrl_mask + pmu->global_status_rsvd = pmu->global_ctrl_rsvd & ~(MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF | MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD); if (vmx_pt_mode_is_host_guest()) - pmu->global_status_mask &= + pmu->global_status_rsvd &= ~MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI; entry = kvm_find_cpuid_entry_index(vcpu, 7, 0); @@ -533,7 +587,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters); perf_capabilities = vcpu_get_perf_capabilities(vcpu); - if (cpuid_model_is_consistent(vcpu) && + if (intel_pmu_lbr_is_compatible(vcpu) && (perf_capabilities & PMU_CAP_LBR_FMT)) memcpy(&lbr_desc->records, &vmx_lbr_caps, sizeof(vmx_lbr_caps)); else @@ -544,15 +598,12 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) if (perf_capabilities & PERF_CAP_PEBS_FORMAT) { if (perf_capabilities & PERF_CAP_PEBS_BASELINE) { - pmu->pebs_enable_mask = counter_mask; + pmu->pebs_enable_rsvd = counter_rsvd; pmu->reserved_bits &= ~ICL_EVENTSEL_ADAPTIVE; - for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { - pmu->fixed_ctr_ctrl_mask &= - ~(1ULL << (KVM_FIXED_PMC_BASE_IDX + i * 4)); - } - pmu->pebs_data_cfg_mask = ~0xff00000full; + pmu->pebs_data_cfg_rsvd = ~0xff00000full; + intel_pmu_enable_fixed_counter_bits(pmu, ICL_FIXED_0_ADAPTIVE); } else { - pmu->pebs_enable_mask = + pmu->pebs_enable_rsvd = ~((1ull << pmu->nr_arch_gp_counters) - 1); } } @@ -564,14 +615,17 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); - for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) { + if (!lbr_desc) + return; + + for (i = 0; i < KVM_MAX_NR_INTEL_GP_COUNTERS; i++) { pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; pmu->gp_counters[i].current_config = 0; } - for (i = 0; i < KVM_PMC_MAX_FIXED; i++) { + for (i = 0; i < KVM_MAX_NR_INTEL_FIXED_COUTNERS; i++) { pmu->fixed_counters[i].type = KVM_PMC_FIXED; pmu->fixed_counters[i].vcpu = vcpu; pmu->fixed_counters[i].idx = i + KVM_FIXED_PMC_BASE_IDX; @@ -671,6 +725,9 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + if (WARN_ON_ONCE(!lbr_desc)) + return; + if (!lbr_desc->event) { vmx_disable_lbr_msrs_passthrough(vcpu); if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR) @@ -731,6 +788,6 @@ struct kvm_pmu_ops intel_pmu_ops __initdata = { .deliver_pmi = intel_pmu_deliver_pmi, .cleanup = intel_pmu_cleanup, .EVENTSEL_EVENT = ARCH_PERFMON_EVENTSEL_EVENT, - .MAX_NR_GP_COUNTERS = KVM_INTEL_PMC_MAX_GENERIC, + .MAX_NR_GP_COUNTERS = KVM_MAX_NR_INTEL_GP_COUNTERS, .MIN_NR_GP_COUNTERS = 1, }; diff --git a/arch/x86/kvm/vmx/pmu_intel.h b/arch/x86/kvm/vmx/pmu_intel.h new file mode 100644 index 000000000000..5620d0882cdc --- /dev/null +++ b/arch/x86/kvm/vmx/pmu_intel.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_VMX_PMU_INTEL_H +#define __KVM_X86_VMX_PMU_INTEL_H + +#include <linux/kvm_host.h> + +bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu); +int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu); + +struct lbr_desc { + /* Basic info about guest LBR records. */ + struct x86_pmu_lbr records; + + /* + * Emulate LBR feature via passthrough LBR registers when the + * per-vcpu guest LBR event is scheduled on the current pcpu. + * + * The records may be inaccurate if the host reclaims the LBR. + */ + struct perf_event *event; + + /* True if LBRs are marked as not intercepted in the MSR bitmap */ + bool msr_passthrough; +}; + +extern struct x86_pmu_lbr vmx_lbr_caps; + +#endif /* __KVM_X86_VMX_PMU_INTEL_H */ diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index af662312fd07..99d1d599ff8c 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -11,6 +11,7 @@ #include "posted_intr.h" #include "trace.h" #include "vmx.h" +#include "tdx.h" /* * Maintain a per-CPU list of vCPUs that need to be awakened by wakeup_handler() @@ -31,9 +32,11 @@ static DEFINE_PER_CPU(struct list_head, wakeup_vcpus_on_cpu); */ static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock); -static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) +#define PI_LOCK_SCHED_OUT SINGLE_DEPTH_NESTING + +struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) { - return &(to_vmx(vcpu)->pi_desc); + return &(to_vt(vcpu)->pi_desc); } static int pi_try_set_control(struct pi_desc *pi_desc, u64 *pold, u64 new) @@ -53,7 +56,7 @@ static int pi_try_set_control(struct pi_desc *pi_desc, u64 *pold, u64 new) void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vcpu_vt *vt = to_vt(vcpu); struct pi_desc old, new; unsigned long flags; unsigned int dest; @@ -89,9 +92,20 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) * current pCPU if the task was migrated. */ if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) { - raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu)); - list_del(&vmx->pi_wakeup_list); - raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu)); + raw_spinlock_t *spinlock = &per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu); + + /* + * In addition to taking the wakeup lock for the regular/IRQ + * context, tell lockdep it is being taken for the "sched out" + * context as well. vCPU loads happens in task context, and + * this is taking the lock of the *previous* CPU, i.e. can race + * with both the scheduler and the wakeup handler. + */ + raw_spin_lock(spinlock); + spin_acquire(&spinlock->dep_map, PI_LOCK_SCHED_OUT, 0, _RET_IP_); + list_del(&vt->pi_wakeup_list); + spin_release(&spinlock->dep_map, _RET_IP_); + raw_spin_unlock(spinlock); } dest = cpu_physical_id(cpu); @@ -107,7 +121,7 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) * handle task migration (@cpu != vcpu->cpu). */ new.ndst = dest; - new.sn = 0; + __pi_clear_sn(&new); /* * Restore the notification vector; in the blocking case, the @@ -146,18 +160,30 @@ static bool vmx_can_use_vtd_pi(struct kvm *kvm) static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vcpu_vt *vt = to_vt(vcpu); struct pi_desc old, new; - unsigned long flags; - local_irq_save(flags); + lockdep_assert_irqs_disabled(); - raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu)); - list_add_tail(&vmx->pi_wakeup_list, + /* + * Acquire the wakeup lock using the "sched out" context to workaround + * a lockdep false positive. When this is called, schedule() holds + * various per-CPU scheduler locks. When the wakeup handler runs, it + * holds this CPU's wakeup lock while calling try_to_wake_up(), which + * can eventually take the aforementioned scheduler locks, which causes + * lockdep to assume there is deadlock. + * + * Deadlock can't actually occur because IRQs are disabled for the + * entirety of the sched_out critical section, i.e. the wakeup handler + * can't run while the scheduler locks are held. + */ + raw_spin_lock_nested(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu), + PI_LOCK_SCHED_OUT); + list_add_tail(&vt->pi_wakeup_list, &per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu)); raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu)); - WARN(pi_desc->sn, "PI descriptor SN field set before blocking"); + WARN(pi_test_sn(pi_desc), "PI descriptor SN field set before blocking"); old.control = READ_ONCE(pi_desc->control); do { @@ -176,8 +202,6 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu) */ if (pi_test_on(&new)) __apic_send_IPI_self(POSTED_INTR_WAKEUP_VECTOR); - - local_irq_restore(flags); } static bool vmx_needs_pi_wakeup(struct kvm_vcpu *vcpu) @@ -190,7 +214,8 @@ static bool vmx_needs_pi_wakeup(struct kvm_vcpu *vcpu) * notification vector is switched to the one that calls * back to the pi_wakeup_handler() function. */ - return vmx_can_use_ipiv(vcpu) || vmx_can_use_vtd_pi(vcpu->kvm); + return (vmx_can_use_ipiv(vcpu) && !is_td_vcpu(vcpu)) || + vmx_can_use_vtd_pi(vcpu->kvm); } void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) @@ -200,7 +225,9 @@ void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) if (!vmx_needs_pi_wakeup(vcpu)) return; - if (kvm_vcpu_is_blocking(vcpu) && !vmx_interrupt_blocked(vcpu)) + if (kvm_vcpu_is_blocking(vcpu) && + ((is_td_vcpu(vcpu) && tdx_interrupt_allowed(vcpu)) || + (!is_td_vcpu(vcpu) && !vmx_interrupt_blocked(vcpu)))) pi_enable_wakeup_handler(vcpu); /* @@ -220,13 +247,13 @@ void pi_wakeup_handler(void) int cpu = smp_processor_id(); struct list_head *wakeup_list = &per_cpu(wakeup_vcpus_on_cpu, cpu); raw_spinlock_t *spinlock = &per_cpu(wakeup_vcpus_on_cpu_lock, cpu); - struct vcpu_vmx *vmx; + struct vcpu_vt *vt; raw_spin_lock(spinlock); - list_for_each_entry(vmx, wakeup_list, pi_wakeup_list) { + list_for_each_entry(vt, wakeup_list, pi_wakeup_list) { - if (pi_test_on(&vmx->pi_desc)) - kvm_vcpu_wake_up(&vmx->vcpu); + if (pi_test_on(&vt->pi_desc)) + kvm_vcpu_wake_up(vt_to_vcpu(vt)); } raw_spin_unlock(spinlock); } @@ -274,6 +301,7 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, { struct kvm_kernel_irq_routing_entry *e; struct kvm_irq_routing_table *irq_rt; + bool enable_remapped_mode = true; struct kvm_lapic_irq irq; struct kvm_vcpu *vcpu; struct vcpu_data vcpu_info; @@ -312,21 +340,8 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, kvm_set_msi_irq(kvm, e, &irq); if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || - !kvm_irq_is_postable(&irq)) { - /* - * Make sure the IRTE is in remapped mode if - * we don't handle it in posted mode. - */ - ret = irq_set_vcpu_affinity(host_irq, NULL); - if (ret < 0) { - printk(KERN_INFO - "failed to back to remapped mode, irq: %u\n", - host_irq); - goto out; - } - + !kvm_irq_is_postable(&irq)) continue; - } vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)); vcpu_info.vector = irq.vector; @@ -334,11 +349,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi, vcpu_info.vector, vcpu_info.pi_desc_addr, set); - if (set) - ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); - else - ret = irq_set_vcpu_affinity(host_irq, NULL); + if (!set) + continue; + + enable_remapped_mode = false; + ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); if (ret < 0) { printk(KERN_INFO "%s: failed to update PI IRTE\n", __func__); @@ -346,6 +362,9 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, } } + if (enable_remapped_mode) + ret = irq_set_vcpu_affinity(host_irq, NULL); + ret = 0; out: srcu_read_unlock(&kvm->irq_srcu, idx); diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 26992076552e..68605ca7ef68 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -2,97 +2,10 @@ #ifndef __KVM_X86_VMX_POSTED_INTR_H #define __KVM_X86_VMX_POSTED_INTR_H -#define POSTED_INTR_ON 0 -#define POSTED_INTR_SN 1 +#include <linux/bitmap.h> +#include <asm/posted_intr.h> -#define PID_TABLE_ENTRY_VALID 1 - -/* Posted-Interrupt Descriptor */ -struct pi_desc { - u32 pir[8]; /* Posted interrupt requested */ - union { - struct { - /* bit 256 - Outstanding Notification */ - u16 on : 1, - /* bit 257 - Suppress Notification */ - sn : 1, - /* bit 271:258 - Reserved */ - rsvd_1 : 14; - /* bit 279:272 - Notification Vector */ - u8 nv; - /* bit 287:280 - Reserved */ - u8 rsvd_2; - /* bit 319:288 - Notification Destination */ - u32 ndst; - }; - u64 control; - }; - u32 rsvd[6]; -} __aligned(64); - -static inline bool pi_test_and_set_on(struct pi_desc *pi_desc) -{ - return test_and_set_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc) -{ - return test_and_clear_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc) -{ - return test_and_clear_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) -{ - return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); -} - -static inline bool pi_is_pir_empty(struct pi_desc *pi_desc) -{ - return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS); -} - -static inline void pi_set_sn(struct pi_desc *pi_desc) -{ - set_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} - -static inline void pi_set_on(struct pi_desc *pi_desc) -{ - set_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline void pi_clear_on(struct pi_desc *pi_desc) -{ - clear_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline void pi_clear_sn(struct pi_desc *pi_desc) -{ - clear_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_on(struct pi_desc *pi_desc) -{ - return test_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_sn(struct pi_desc *pi_desc) -{ - return test_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} +struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu); void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu); void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu); @@ -103,4 +16,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void vmx_pi_start_assignment(struct kvm *kvm); +static inline int pi_find_highest_vector(struct pi_desc *pi_desc) +{ + int vec; + + vec = find_last_bit((unsigned long *)pi_desc->pir, 256); + return vec < 256 ? vec : -1; +} + #endif /* __KVM_X86_VMX_POSTED_INTR_H */ diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 6fef01e0536e..df1d0cf76947 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -2,14 +2,14 @@ /* Copyright(c) 2021 Intel Corporation. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <asm/msr.h> #include <asm/sgx.h> -#include "cpuid.h" +#include "x86.h" #include "kvm_cache_regs.h" #include "nested.h" #include "sgx.h" #include "vmx.h" -#include "x86.h" bool __read_mostly enable_sgx = 1; module_param_named(sgx, enable_sgx, bool, 0444); @@ -38,7 +38,7 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset, fault = true; } else if (likely(is_64_bit_mode(vcpu))) { *gva = vmx_get_untagged_addr(vcpu, *gva, 0); - fault = is_noncanonical_address(*gva, vcpu); + fault = is_noncanonical_address(*gva, vcpu, 0); } else { *gva &= 0xffffffff; fault = (s.unusable) || @@ -123,7 +123,7 @@ static int sgx_inject_fault(struct kvm_vcpu *vcpu, gva_t gva, int trapnr) * likely than a bad userspace address. */ if ((trapnr == PF_VECTOR || !boot_cpu_has(X86_FEATURE_SGX2)) && - guest_cpuid_has(vcpu, X86_FEATURE_SGX2)) { + guest_cpu_cap_has(vcpu, X86_FEATURE_SGX2)) { memset(&ex, 0, sizeof(ex)); ex.vector = PF_VECTOR; ex.error_code = PFERR_PRESENT_MASK | PFERR_WRITE_MASK | @@ -274,7 +274,7 @@ static int handle_encls_ecreate(struct kvm_vcpu *vcpu) * simultaneously set SGX_ATTR_PROVISIONKEY to bypass the check to * enforce restriction of access to the PROVISIONKEY. */ - contents = (struct sgx_secs *)__get_free_page(GFP_KERNEL_ACCOUNT); + contents = (struct sgx_secs *)__get_free_page(GFP_KERNEL); if (!contents) return -ENOMEM; @@ -366,7 +366,7 @@ static inline bool encls_leaf_enabled_in_guest(struct kvm_vcpu *vcpu, u32 leaf) return true; if (leaf >= EAUG && leaf <= EMODT) - return guest_cpuid_has(vcpu, X86_FEATURE_SGX2); + return guest_cpu_cap_has(vcpu, X86_FEATURE_SGX2); return false; } @@ -382,8 +382,8 @@ int handle_encls(struct kvm_vcpu *vcpu) { u32 leaf = (u32)kvm_rax_read(vcpu); - if (!enable_sgx || !guest_cpuid_has(vcpu, X86_FEATURE_SGX) || - !guest_cpuid_has(vcpu, X86_FEATURE_SGX1)) { + if (!enable_sgx || !guest_cpu_cap_has(vcpu, X86_FEATURE_SGX) || + !guest_cpu_cap_has(vcpu, X86_FEATURE_SGX1)) { kvm_queue_exception(vcpu, UD_VECTOR); } else if (!encls_leaf_enabled_in_guest(vcpu, leaf) || !sgx_enabled_in_guest_bios(vcpu) || !is_paging(vcpu)) { @@ -412,16 +412,16 @@ void setup_default_sgx_lepubkeyhash(void) * MSRs exist but are read-only (locked and not writable). */ if (!enable_sgx || boot_cpu_has(X86_FEATURE_SGX_LC) || - rdmsrl_safe(MSR_IA32_SGXLEPUBKEYHASH0, &sgx_pubkey_hash[0])) { + rdmsrq_safe(MSR_IA32_SGXLEPUBKEYHASH0, &sgx_pubkey_hash[0])) { sgx_pubkey_hash[0] = 0xa6053e051270b7acULL; sgx_pubkey_hash[1] = 0x6cfbe8ba8b3b413dULL; sgx_pubkey_hash[2] = 0xc4916d99f2b3735dULL; sgx_pubkey_hash[3] = 0xd4f8c05909f9bb3bULL; } else { /* MSR_IA32_SGXLEPUBKEYHASH0 is read above */ - rdmsrl(MSR_IA32_SGXLEPUBKEYHASH1, sgx_pubkey_hash[1]); - rdmsrl(MSR_IA32_SGXLEPUBKEYHASH2, sgx_pubkey_hash[2]); - rdmsrl(MSR_IA32_SGXLEPUBKEYHASH3, sgx_pubkey_hash[3]); + rdmsrq(MSR_IA32_SGXLEPUBKEYHASH1, sgx_pubkey_hash[1]); + rdmsrq(MSR_IA32_SGXLEPUBKEYHASH2, sgx_pubkey_hash[2]); + rdmsrq(MSR_IA32_SGXLEPUBKEYHASH3, sgx_pubkey_hash[3]); } } @@ -480,15 +480,15 @@ void vmx_write_encls_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (!cpu_has_vmx_encls_vmexit()) return; - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX) && sgx_enabled_in_guest_bios(vcpu)) { - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX1)) { + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX1)) { bitmap &= ~GENMASK_ULL(ETRACK, ECREATE); if (sgx_intercept_encls_ecreate(vcpu)) bitmap |= (1 << ECREATE); } - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX2)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX2)) bitmap &= ~GENMASK_ULL(EMODT, EAUG); /* diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c new file mode 100644 index 000000000000..b952bc673271 --- /dev/null +++ b/arch/x86/kvm/vmx/tdx.c @@ -0,0 +1,3526 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/cleanup.h> +#include <linux/cpu.h> +#include <asm/cpufeature.h> +#include <asm/fpu/xcr.h> +#include <linux/misc_cgroup.h> +#include <linux/mmu_context.h> +#include <asm/tdx.h> +#include "capabilities.h" +#include "mmu.h" +#include "x86_ops.h" +#include "lapic.h" +#include "tdx.h" +#include "vmx.h" +#include "mmu/spte.h" +#include "common.h" +#include "posted_intr.h" +#include "irq.h" +#include <trace/events/kvm.h> +#include "trace.h" + +#pragma GCC poison to_vmx + +#undef pr_fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#define pr_tdx_error(__fn, __err) \ + pr_err_ratelimited("SEAMCALL %s failed: 0x%llx\n", #__fn, __err) + +#define __pr_tdx_error_N(__fn_str, __err, __fmt, ...) \ + pr_err_ratelimited("SEAMCALL " __fn_str " failed: 0x%llx, " __fmt, __err, __VA_ARGS__) + +#define pr_tdx_error_1(__fn, __err, __rcx) \ + __pr_tdx_error_N(#__fn, __err, "rcx 0x%llx\n", __rcx) + +#define pr_tdx_error_2(__fn, __err, __rcx, __rdx) \ + __pr_tdx_error_N(#__fn, __err, "rcx 0x%llx, rdx 0x%llx\n", __rcx, __rdx) + +#define pr_tdx_error_3(__fn, __err, __rcx, __rdx, __r8) \ + __pr_tdx_error_N(#__fn, __err, "rcx 0x%llx, rdx 0x%llx, r8 0x%llx\n", __rcx, __rdx, __r8) + +bool enable_tdx __ro_after_init; +module_param_named(tdx, enable_tdx, bool, 0444); + +#define TDX_SHARED_BIT_PWL_5 gpa_to_gfn(BIT_ULL(51)) +#define TDX_SHARED_BIT_PWL_4 gpa_to_gfn(BIT_ULL(47)) + +static enum cpuhp_state tdx_cpuhp_state; + +static const struct tdx_sys_info *tdx_sysinfo; + +void tdh_vp_rd_failed(struct vcpu_tdx *tdx, char *uclass, u32 field, u64 err) +{ + KVM_BUG_ON(1, tdx->vcpu.kvm); + pr_err("TDH_VP_RD[%s.0x%x] failed 0x%llx\n", uclass, field, err); +} + +void tdh_vp_wr_failed(struct vcpu_tdx *tdx, char *uclass, char *op, u32 field, + u64 val, u64 err) +{ + KVM_BUG_ON(1, tdx->vcpu.kvm); + pr_err("TDH_VP_WR[%s.0x%x]%s0x%llx failed: 0x%llx\n", uclass, field, op, val, err); +} + +#define KVM_SUPPORTED_TD_ATTRS (TDX_TD_ATTR_SEPT_VE_DISABLE) + +static __always_inline struct kvm_tdx *to_kvm_tdx(struct kvm *kvm) +{ + return container_of(kvm, struct kvm_tdx, kvm); +} + +static __always_inline struct vcpu_tdx *to_tdx(struct kvm_vcpu *vcpu) +{ + return container_of(vcpu, struct vcpu_tdx, vcpu); +} + +static u64 tdx_get_supported_attrs(const struct tdx_sys_info_td_conf *td_conf) +{ + u64 val = KVM_SUPPORTED_TD_ATTRS; + + if ((val & td_conf->attributes_fixed1) != td_conf->attributes_fixed1) + return 0; + + val &= td_conf->attributes_fixed0; + + return val; +} + +static u64 tdx_get_supported_xfam(const struct tdx_sys_info_td_conf *td_conf) +{ + u64 val = kvm_caps.supported_xcr0 | kvm_caps.supported_xss; + + if ((val & td_conf->xfam_fixed1) != td_conf->xfam_fixed1) + return 0; + + val &= td_conf->xfam_fixed0; + + return val; +} + +static int tdx_get_guest_phys_addr_bits(const u32 eax) +{ + return (eax & GENMASK(23, 16)) >> 16; +} + +static u32 tdx_set_guest_phys_addr_bits(const u32 eax, int addr_bits) +{ + return (eax & ~GENMASK(23, 16)) | (addr_bits & 0xff) << 16; +} + +#define TDX_FEATURE_TSX (__feature_bit(X86_FEATURE_HLE) | __feature_bit(X86_FEATURE_RTM)) + +static bool has_tsx(const struct kvm_cpuid_entry2 *entry) +{ + return entry->function == 7 && entry->index == 0 && + (entry->ebx & TDX_FEATURE_TSX); +} + +static void clear_tsx(struct kvm_cpuid_entry2 *entry) +{ + entry->ebx &= ~TDX_FEATURE_TSX; +} + +static bool has_waitpkg(const struct kvm_cpuid_entry2 *entry) +{ + return entry->function == 7 && entry->index == 0 && + (entry->ecx & __feature_bit(X86_FEATURE_WAITPKG)); +} + +static void clear_waitpkg(struct kvm_cpuid_entry2 *entry) +{ + entry->ecx &= ~__feature_bit(X86_FEATURE_WAITPKG); +} + +static void tdx_clear_unsupported_cpuid(struct kvm_cpuid_entry2 *entry) +{ + if (has_tsx(entry)) + clear_tsx(entry); + + if (has_waitpkg(entry)) + clear_waitpkg(entry); +} + +static bool tdx_unsupported_cpuid(const struct kvm_cpuid_entry2 *entry) +{ + return has_tsx(entry) || has_waitpkg(entry); +} + +#define KVM_TDX_CPUID_NO_SUBLEAF ((__u32)-1) + +static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char idx) +{ + const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf; + + entry->function = (u32)td_conf->cpuid_config_leaves[idx]; + entry->index = td_conf->cpuid_config_leaves[idx] >> 32; + entry->eax = (u32)td_conf->cpuid_config_values[idx][0]; + entry->ebx = td_conf->cpuid_config_values[idx][0] >> 32; + entry->ecx = (u32)td_conf->cpuid_config_values[idx][1]; + entry->edx = td_conf->cpuid_config_values[idx][1] >> 32; + + if (entry->index == KVM_TDX_CPUID_NO_SUBLEAF) + entry->index = 0; + + /* + * The TDX module doesn't allow configuring the guest phys addr bits + * (EAX[23:16]). However, KVM uses it as an interface to the userspace + * to configure the GPAW. Report these bits as configurable. + */ + if (entry->function == 0x80000008) + entry->eax = tdx_set_guest_phys_addr_bits(entry->eax, 0xff); + + tdx_clear_unsupported_cpuid(entry); +} + +static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf, + struct kvm_tdx_capabilities *caps) +{ + int i; + + caps->supported_attrs = tdx_get_supported_attrs(td_conf); + if (!caps->supported_attrs) + return -EIO; + + caps->supported_xfam = tdx_get_supported_xfam(td_conf); + if (!caps->supported_xfam) + return -EIO; + + caps->cpuid.nent = td_conf->num_cpuid_config; + + for (i = 0; i < td_conf->num_cpuid_config; i++) + td_init_cpuid_entry2(&caps->cpuid.entries[i], i); + + return 0; +} + +/* + * Some SEAMCALLs acquire the TDX module globally, and can fail with + * TDX_OPERAND_BUSY. Use a global mutex to serialize these SEAMCALLs. + */ +static DEFINE_MUTEX(tdx_lock); + +static atomic_t nr_configured_hkid; + +static bool tdx_operand_busy(u64 err) +{ + return (err & TDX_SEAMCALL_STATUS_MASK) == TDX_OPERAND_BUSY; +} + + +/* + * A per-CPU list of TD vCPUs associated with a given CPU. + * Protected by interrupt mask. Only manipulated by the CPU owning this per-CPU + * list. + * - When a vCPU is loaded onto a CPU, it is removed from the per-CPU list of + * the old CPU during the IPI callback running on the old CPU, and then added + * to the per-CPU list of the new CPU. + * - When a TD is tearing down, all vCPUs are disassociated from their current + * running CPUs and removed from the per-CPU list during the IPI callback + * running on those CPUs. + * - When a CPU is brought down, traverse the per-CPU list to disassociate all + * associated TD vCPUs and remove them from the per-CPU list. + */ +static DEFINE_PER_CPU(struct list_head, associated_tdvcpus); + +static __always_inline unsigned long tdvmcall_exit_type(struct kvm_vcpu *vcpu) +{ + return to_tdx(vcpu)->vp_enter_args.r10; +} + +static __always_inline unsigned long tdvmcall_leaf(struct kvm_vcpu *vcpu) +{ + return to_tdx(vcpu)->vp_enter_args.r11; +} + +static __always_inline void tdvmcall_set_return_code(struct kvm_vcpu *vcpu, + long val) +{ + to_tdx(vcpu)->vp_enter_args.r10 = val; +} + +static __always_inline void tdvmcall_set_return_val(struct kvm_vcpu *vcpu, + unsigned long val) +{ + to_tdx(vcpu)->vp_enter_args.r11 = val; +} + +static inline void tdx_hkid_free(struct kvm_tdx *kvm_tdx) +{ + tdx_guest_keyid_free(kvm_tdx->hkid); + kvm_tdx->hkid = -1; + atomic_dec(&nr_configured_hkid); + misc_cg_uncharge(MISC_CG_RES_TDX, kvm_tdx->misc_cg, 1); + put_misc_cg(kvm_tdx->misc_cg); + kvm_tdx->misc_cg = NULL; +} + +static inline bool is_hkid_assigned(struct kvm_tdx *kvm_tdx) +{ + return kvm_tdx->hkid > 0; +} + +static inline void tdx_disassociate_vp(struct kvm_vcpu *vcpu) +{ + lockdep_assert_irqs_disabled(); + + list_del(&to_tdx(vcpu)->cpu_list); + + /* + * Ensure tdx->cpu_list is updated before setting vcpu->cpu to -1, + * otherwise, a different CPU can see vcpu->cpu = -1 and add the vCPU + * to its list before it's deleted from this CPU's list. + */ + smp_wmb(); + + vcpu->cpu = -1; +} + +static void tdx_clear_page(struct page *page) +{ + const void *zero_page = (const void *) page_to_virt(ZERO_PAGE(0)); + void *dest = page_to_virt(page); + unsigned long i; + + /* + * The page could have been poisoned. MOVDIR64B also clears + * the poison bit so the kernel can safely use the page again. + */ + for (i = 0; i < PAGE_SIZE; i += 64) + movdir64b(dest + i, zero_page); + /* + * MOVDIR64B store uses WC buffer. Prevent following memory reads + * from seeing potentially poisoned cache. + */ + __mb(); +} + +static void tdx_no_vcpus_enter_start(struct kvm *kvm) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + + lockdep_assert_held_write(&kvm->mmu_lock); + + WRITE_ONCE(kvm_tdx->wait_for_sept_zap, true); + + kvm_make_all_cpus_request(kvm, KVM_REQ_OUTSIDE_GUEST_MODE); +} + +static void tdx_no_vcpus_enter_stop(struct kvm *kvm) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + + lockdep_assert_held_write(&kvm->mmu_lock); + + WRITE_ONCE(kvm_tdx->wait_for_sept_zap, false); +} + +/* TDH.PHYMEM.PAGE.RECLAIM is allowed only when destroying the TD. */ +static int __tdx_reclaim_page(struct page *page) +{ + u64 err, rcx, rdx, r8; + + err = tdh_phymem_page_reclaim(page, &rcx, &rdx, &r8); + + /* + * No need to check for TDX_OPERAND_BUSY; all TD pages are freed + * before the HKID is released and control pages have also been + * released at this point, so there is no possibility of contention. + */ + if (WARN_ON_ONCE(err)) { + pr_tdx_error_3(TDH_PHYMEM_PAGE_RECLAIM, err, rcx, rdx, r8); + return -EIO; + } + return 0; +} + +static int tdx_reclaim_page(struct page *page) +{ + int r; + + r = __tdx_reclaim_page(page); + if (!r) + tdx_clear_page(page); + return r; +} + + +/* + * Reclaim the TD control page(s) which are crypto-protected by TDX guest's + * private KeyID. Assume the cache associated with the TDX private KeyID has + * been flushed. + */ +static void tdx_reclaim_control_page(struct page *ctrl_page) +{ + /* + * Leak the page if the kernel failed to reclaim the page. + * The kernel cannot use it safely anymore. + */ + if (tdx_reclaim_page(ctrl_page)) + return; + + __free_page(ctrl_page); +} + +struct tdx_flush_vp_arg { + struct kvm_vcpu *vcpu; + u64 err; +}; + +static void tdx_flush_vp(void *_arg) +{ + struct tdx_flush_vp_arg *arg = _arg; + struct kvm_vcpu *vcpu = arg->vcpu; + u64 err; + + arg->err = 0; + lockdep_assert_irqs_disabled(); + + /* Task migration can race with CPU offlining. */ + if (unlikely(vcpu->cpu != raw_smp_processor_id())) + return; + + /* + * No need to do TDH_VP_FLUSH if the vCPU hasn't been initialized. The + * list tracking still needs to be updated so that it's correct if/when + * the vCPU does get initialized. + */ + if (to_tdx(vcpu)->state != VCPU_TD_STATE_UNINITIALIZED) { + /* + * No need to retry. TDX Resources needed for TDH.VP.FLUSH are: + * TDVPR as exclusive, TDR as shared, and TDCS as shared. This + * vp flush function is called when destructing vCPU/TD or vCPU + * migration. No other thread uses TDVPR in those cases. + */ + err = tdh_vp_flush(&to_tdx(vcpu)->vp); + if (unlikely(err && err != TDX_VCPU_NOT_ASSOCIATED)) { + /* + * This function is called in IPI context. Do not use + * printk to avoid console semaphore. + * The caller prints out the error message, instead. + */ + if (err) + arg->err = err; + } + } + + tdx_disassociate_vp(vcpu); +} + +static void tdx_flush_vp_on_cpu(struct kvm_vcpu *vcpu) +{ + struct tdx_flush_vp_arg arg = { + .vcpu = vcpu, + }; + int cpu = vcpu->cpu; + + if (unlikely(cpu == -1)) + return; + + smp_call_function_single(cpu, tdx_flush_vp, &arg, 1); + if (KVM_BUG_ON(arg.err, vcpu->kvm)) + pr_tdx_error(TDH_VP_FLUSH, arg.err); +} + +void tdx_disable_virtualization_cpu(void) +{ + int cpu = raw_smp_processor_id(); + struct list_head *tdvcpus = &per_cpu(associated_tdvcpus, cpu); + struct tdx_flush_vp_arg arg; + struct vcpu_tdx *tdx, *tmp; + unsigned long flags; + + local_irq_save(flags); + /* Safe variant needed as tdx_disassociate_vp() deletes the entry. */ + list_for_each_entry_safe(tdx, tmp, tdvcpus, cpu_list) { + arg.vcpu = &tdx->vcpu; + tdx_flush_vp(&arg); + } + local_irq_restore(flags); +} + +#define TDX_SEAMCALL_RETRIES 10000 + +static void smp_func_do_phymem_cache_wb(void *unused) +{ + u64 err = 0; + bool resume; + int i; + + /* + * TDH.PHYMEM.CACHE.WB flushes caches associated with any TDX private + * KeyID on the package or core. The TDX module may not finish the + * cache flush but return TDX_INTERRUPTED_RESUMEABLE instead. The + * kernel should retry it until it returns success w/o rescheduling. + */ + for (i = TDX_SEAMCALL_RETRIES; i > 0; i--) { + resume = !!err; + err = tdh_phymem_cache_wb(resume); + switch (err) { + case TDX_INTERRUPTED_RESUMABLE: + continue; + case TDX_NO_HKID_READY_TO_WBCACHE: + err = TDX_SUCCESS; /* Already done by other thread */ + fallthrough; + default: + goto out; + } + } + +out: + if (WARN_ON_ONCE(err)) + pr_tdx_error(TDH_PHYMEM_CACHE_WB, err); +} + +void tdx_mmu_release_hkid(struct kvm *kvm) +{ + bool packages_allocated, targets_allocated; + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + cpumask_var_t packages, targets; + struct kvm_vcpu *vcpu; + unsigned long j; + int i; + u64 err; + + if (!is_hkid_assigned(kvm_tdx)) + return; + + packages_allocated = zalloc_cpumask_var(&packages, GFP_KERNEL); + targets_allocated = zalloc_cpumask_var(&targets, GFP_KERNEL); + cpus_read_lock(); + + kvm_for_each_vcpu(j, vcpu, kvm) + tdx_flush_vp_on_cpu(vcpu); + + /* + * TDH.PHYMEM.CACHE.WB tries to acquire the TDX module global lock + * and can fail with TDX_OPERAND_BUSY when it fails to get the lock. + * Multiple TDX guests can be destroyed simultaneously. Take the + * mutex to prevent it from getting error. + */ + mutex_lock(&tdx_lock); + + /* + * Releasing HKID is in vm_destroy(). + * After the above flushing vps, there should be no more vCPU + * associations, as all vCPU fds have been released at this stage. + */ + err = tdh_mng_vpflushdone(&kvm_tdx->td); + if (err == TDX_FLUSHVP_NOT_DONE) + goto out; + if (KVM_BUG_ON(err, kvm)) { + pr_tdx_error(TDH_MNG_VPFLUSHDONE, err); + pr_err("tdh_mng_vpflushdone() failed. HKID %d is leaked.\n", + kvm_tdx->hkid); + goto out; + } + + for_each_online_cpu(i) { + if (packages_allocated && + cpumask_test_and_set_cpu(topology_physical_package_id(i), + packages)) + continue; + if (targets_allocated) + cpumask_set_cpu(i, targets); + } + if (targets_allocated) + on_each_cpu_mask(targets, smp_func_do_phymem_cache_wb, NULL, true); + else + on_each_cpu(smp_func_do_phymem_cache_wb, NULL, true); + /* + * In the case of error in smp_func_do_phymem_cache_wb(), the following + * tdh_mng_key_freeid() will fail. + */ + err = tdh_mng_key_freeid(&kvm_tdx->td); + if (KVM_BUG_ON(err, kvm)) { + pr_tdx_error(TDH_MNG_KEY_FREEID, err); + pr_err("tdh_mng_key_freeid() failed. HKID %d is leaked.\n", + kvm_tdx->hkid); + } else { + tdx_hkid_free(kvm_tdx); + } + +out: + mutex_unlock(&tdx_lock); + cpus_read_unlock(); + free_cpumask_var(targets); + free_cpumask_var(packages); +} + +static void tdx_reclaim_td_control_pages(struct kvm *kvm) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + u64 err; + int i; + + /* + * tdx_mmu_release_hkid() failed to reclaim HKID. Something went wrong + * heavily with TDX module. Give up freeing TD pages. As the function + * already warned, don't warn it again. + */ + if (is_hkid_assigned(kvm_tdx)) + return; + + if (kvm_tdx->td.tdcs_pages) { + for (i = 0; i < kvm_tdx->td.tdcs_nr_pages; i++) { + if (!kvm_tdx->td.tdcs_pages[i]) + continue; + + tdx_reclaim_control_page(kvm_tdx->td.tdcs_pages[i]); + } + kfree(kvm_tdx->td.tdcs_pages); + kvm_tdx->td.tdcs_pages = NULL; + } + + if (!kvm_tdx->td.tdr_page) + return; + + if (__tdx_reclaim_page(kvm_tdx->td.tdr_page)) + return; + + /* + * Use a SEAMCALL to ask the TDX module to flush the cache based on the + * KeyID. TDX module may access TDR while operating on TD (Especially + * when it is reclaiming TDCS). + */ + err = tdh_phymem_page_wbinvd_tdr(&kvm_tdx->td); + if (KVM_BUG_ON(err, kvm)) { + pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err); + return; + } + tdx_clear_page(kvm_tdx->td.tdr_page); + + __free_page(kvm_tdx->td.tdr_page); + kvm_tdx->td.tdr_page = NULL; +} + +void tdx_vm_destroy(struct kvm *kvm) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + + tdx_reclaim_td_control_pages(kvm); + + kvm_tdx->state = TD_STATE_UNINITIALIZED; +} + +static int tdx_do_tdh_mng_key_config(void *param) +{ + struct kvm_tdx *kvm_tdx = param; + u64 err; + + /* TDX_RND_NO_ENTROPY related retries are handled by sc_retry() */ + err = tdh_mng_key_config(&kvm_tdx->td); + + if (KVM_BUG_ON(err, &kvm_tdx->kvm)) { + pr_tdx_error(TDH_MNG_KEY_CONFIG, err); + return -EIO; + } + + return 0; +} + +int tdx_vm_init(struct kvm *kvm) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + + kvm->arch.has_protected_state = true; + kvm->arch.has_private_mem = true; + kvm->arch.disabled_quirks |= KVM_X86_QUIRK_IGNORE_GUEST_PAT; + + /* + * Because guest TD is protected, VMM can't parse the instruction in TD. + * Instead, guest uses MMIO hypercall. For unmodified device driver, + * #VE needs to be injected for MMIO and #VE handler in TD converts MMIO + * instruction into MMIO hypercall. + * + * SPTE value for MMIO needs to be setup so that #VE is injected into + * TD instead of triggering EPT MISCONFIG. + * - RWX=0 so that EPT violation is triggered. + * - suppress #VE bit is cleared to inject #VE. + */ + kvm_mmu_set_mmio_spte_value(kvm, 0); + + /* + * TDX has its own limit of maximum vCPUs it can support for all + * TDX guests in addition to KVM_MAX_VCPUS. TDX module reports + * such limit via the MAX_VCPU_PER_TD global metadata. In + * practice, it reflects the number of logical CPUs that ALL + * platforms that the TDX module supports can possibly have. + * + * Limit TDX guest's maximum vCPUs to the number of logical CPUs + * the platform has. Simply forwarding the MAX_VCPU_PER_TD to + * userspace would result in an unpredictable ABI. + */ + kvm->max_vcpus = min_t(int, kvm->max_vcpus, num_present_cpus()); + + kvm_tdx->state = TD_STATE_UNINITIALIZED; + + return 0; +} + +int tdx_vcpu_create(struct kvm_vcpu *vcpu) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + struct vcpu_tdx *tdx = to_tdx(vcpu); + + if (kvm_tdx->state != TD_STATE_INITIALIZED) + return -EIO; + + /* + * TDX module mandates APICv, which requires an in-kernel local APIC. + * Disallow an in-kernel I/O APIC, because level-triggered interrupts + * and thus the I/O APIC as a whole can't be faithfully emulated in KVM. + */ + if (!irqchip_split(vcpu->kvm)) + return -EINVAL; + + fpstate_set_confidential(&vcpu->arch.guest_fpu); + vcpu->arch.apic->guest_apic_protected = true; + INIT_LIST_HEAD(&tdx->vt.pi_wakeup_list); + + vcpu->arch.efer = EFER_SCE | EFER_LME | EFER_LMA | EFER_NX; + + vcpu->arch.switch_db_regs = KVM_DEBUGREG_AUTO_SWITCH; + vcpu->arch.cr0_guest_owned_bits = -1ul; + vcpu->arch.cr4_guest_owned_bits = -1ul; + + /* KVM can't change TSC offset/multiplier as TDX module manages them. */ + vcpu->arch.guest_tsc_protected = true; + vcpu->arch.tsc_offset = kvm_tdx->tsc_offset; + vcpu->arch.l1_tsc_offset = vcpu->arch.tsc_offset; + vcpu->arch.tsc_scaling_ratio = kvm_tdx->tsc_multiplier; + vcpu->arch.l1_tsc_scaling_ratio = kvm_tdx->tsc_multiplier; + + vcpu->arch.guest_state_protected = + !(to_kvm_tdx(vcpu->kvm)->attributes & TDX_TD_ATTR_DEBUG); + + if ((kvm_tdx->xfam & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE) + vcpu->arch.xfd_no_write_intercept = true; + + tdx->vt.pi_desc.nv = POSTED_INTR_VECTOR; + __pi_set_sn(&tdx->vt.pi_desc); + + tdx->state = VCPU_TD_STATE_UNINITIALIZED; + + return 0; +} + +void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + + vmx_vcpu_pi_load(vcpu, cpu); + if (vcpu->cpu == cpu || !is_hkid_assigned(to_kvm_tdx(vcpu->kvm))) + return; + + tdx_flush_vp_on_cpu(vcpu); + + KVM_BUG_ON(cpu != raw_smp_processor_id(), vcpu->kvm); + local_irq_disable(); + /* + * Pairs with the smp_wmb() in tdx_disassociate_vp() to ensure + * vcpu->cpu is read before tdx->cpu_list. + */ + smp_rmb(); + + list_add(&tdx->cpu_list, &per_cpu(associated_tdvcpus, cpu)); + local_irq_enable(); +} + +bool tdx_interrupt_allowed(struct kvm_vcpu *vcpu) +{ + /* + * KVM can't get the interrupt status of TDX guest and it assumes + * interrupt is always allowed unless TDX guest calls TDVMCALL with HLT, + * which passes the interrupt blocked flag. + */ + return vmx_get_exit_reason(vcpu).basic != EXIT_REASON_HLT || + !to_tdx(vcpu)->vp_enter_args.r12; +} + +bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu) +{ + u64 vcpu_state_details; + + if (pi_has_pending_interrupt(vcpu)) + return true; + + /* + * Only check RVI pending for HALTED case with IRQ enabled. + * For non-HLT cases, KVM doesn't care about STI/SS shadows. And if the + * interrupt was pending before TD exit, then it _must_ be blocked, + * otherwise the interrupt would have been serviced at the instruction + * boundary. + */ + if (vmx_get_exit_reason(vcpu).basic != EXIT_REASON_HLT || + to_tdx(vcpu)->vp_enter_args.r12) + return false; + + vcpu_state_details = + td_state_non_arch_read64(to_tdx(vcpu), TD_VCPU_STATE_DETAILS_NON_ARCH); + + return tdx_vcpu_state_details_intr_pending(vcpu_state_details); +} + +/* + * Compared to vmx_prepare_switch_to_guest(), there is not much to do + * as SEAMCALL/SEAMRET calls take care of most of save and restore. + */ +void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) +{ + struct vcpu_vt *vt = to_vt(vcpu); + + if (vt->guest_state_loaded) + return; + + if (likely(is_64bit_mm(current->mm))) + vt->msr_host_kernel_gs_base = current->thread.gsbase; + else + vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); + + vt->host_debugctlmsr = get_debugctlmsr(); + + vt->guest_state_loaded = true; +} + +struct tdx_uret_msr { + u32 msr; + unsigned int slot; + u64 defval; +}; + +static struct tdx_uret_msr tdx_uret_msrs[] = { + {.msr = MSR_SYSCALL_MASK, .defval = 0x20200 }, + {.msr = MSR_STAR,}, + {.msr = MSR_LSTAR,}, + {.msr = MSR_TSC_AUX,}, +}; + +static void tdx_user_return_msr_update_cache(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(tdx_uret_msrs); i++) + kvm_user_return_msr_update_cache(tdx_uret_msrs[i].slot, + tdx_uret_msrs[i].defval); +} + +static void tdx_prepare_switch_to_host(struct kvm_vcpu *vcpu) +{ + struct vcpu_vt *vt = to_vt(vcpu); + struct vcpu_tdx *tdx = to_tdx(vcpu); + + if (!vt->guest_state_loaded) + return; + + ++vcpu->stat.host_state_reload; + wrmsrl(MSR_KERNEL_GS_BASE, vt->msr_host_kernel_gs_base); + + if (tdx->guest_entered) { + tdx_user_return_msr_update_cache(); + tdx->guest_entered = false; + } + + vt->guest_state_loaded = false; +} + +void tdx_vcpu_put(struct kvm_vcpu *vcpu) +{ + vmx_vcpu_pi_put(vcpu); + tdx_prepare_switch_to_host(vcpu); +} + +void tdx_vcpu_free(struct kvm_vcpu *vcpu) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + struct vcpu_tdx *tdx = to_tdx(vcpu); + int i; + + /* + * It is not possible to reclaim pages while hkid is assigned. It might + * be assigned if: + * 1. the TD VM is being destroyed but freeing hkid failed, in which + * case the pages are leaked + * 2. TD VCPU creation failed and this on the error path, in which case + * there is nothing to do anyway + */ + if (is_hkid_assigned(kvm_tdx)) + return; + + if (tdx->vp.tdcx_pages) { + for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) { + if (tdx->vp.tdcx_pages[i]) + tdx_reclaim_control_page(tdx->vp.tdcx_pages[i]); + } + kfree(tdx->vp.tdcx_pages); + tdx->vp.tdcx_pages = NULL; + } + if (tdx->vp.tdvpr_page) { + tdx_reclaim_control_page(tdx->vp.tdvpr_page); + tdx->vp.tdvpr_page = 0; + } + + tdx->state = VCPU_TD_STATE_UNINITIALIZED; +} + +int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu) +{ + if (unlikely(to_tdx(vcpu)->state != VCPU_TD_STATE_INITIALIZED || + to_kvm_tdx(vcpu->kvm)->state != TD_STATE_RUNNABLE)) + return -EINVAL; + + return 1; +} + +static __always_inline u32 tdcall_to_vmx_exit_reason(struct kvm_vcpu *vcpu) +{ + switch (tdvmcall_leaf(vcpu)) { + case EXIT_REASON_CPUID: + case EXIT_REASON_HLT: + case EXIT_REASON_IO_INSTRUCTION: + case EXIT_REASON_MSR_READ: + case EXIT_REASON_MSR_WRITE: + return tdvmcall_leaf(vcpu); + case EXIT_REASON_EPT_VIOLATION: + return EXIT_REASON_EPT_MISCONFIG; + default: + break; + } + + return EXIT_REASON_TDCALL; +} + +static __always_inline u32 tdx_to_vmx_exit_reason(struct kvm_vcpu *vcpu) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + u32 exit_reason; + + switch (tdx->vp_enter_ret & TDX_SEAMCALL_STATUS_MASK) { + case TDX_SUCCESS: + case TDX_NON_RECOVERABLE_VCPU: + case TDX_NON_RECOVERABLE_TD: + case TDX_NON_RECOVERABLE_TD_NON_ACCESSIBLE: + case TDX_NON_RECOVERABLE_TD_WRONG_APIC_MODE: + break; + default: + return -1u; + } + + exit_reason = tdx->vp_enter_ret; + + switch (exit_reason) { + case EXIT_REASON_TDCALL: + if (tdvmcall_exit_type(vcpu)) + return EXIT_REASON_VMCALL; + + return tdcall_to_vmx_exit_reason(vcpu); + case EXIT_REASON_EPT_MISCONFIG: + /* + * Defer KVM_BUG_ON() until tdx_handle_exit() because this is in + * non-instrumentable code with interrupts disabled. + */ + return -1u; + default: + break; + } + + return exit_reason; +} + +static noinstr void tdx_vcpu_enter_exit(struct kvm_vcpu *vcpu) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + struct vcpu_vt *vt = to_vt(vcpu); + + guest_state_enter_irqoff(); + + tdx->vp_enter_ret = tdh_vp_enter(&tdx->vp, &tdx->vp_enter_args); + + vt->exit_reason.full = tdx_to_vmx_exit_reason(vcpu); + + vt->exit_qualification = tdx->vp_enter_args.rcx; + tdx->ext_exit_qualification = tdx->vp_enter_args.rdx; + tdx->exit_gpa = tdx->vp_enter_args.r8; + vt->exit_intr_info = tdx->vp_enter_args.r9; + + vmx_handle_nmi(vcpu); + + guest_state_exit_irqoff(); +} + +static bool tdx_failed_vmentry(struct kvm_vcpu *vcpu) +{ + return vmx_get_exit_reason(vcpu).failed_vmentry && + vmx_get_exit_reason(vcpu).full != -1u; +} + +static fastpath_t tdx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) +{ + u64 vp_enter_ret = to_tdx(vcpu)->vp_enter_ret; + + /* + * TDX_OPERAND_BUSY could be returned for SEPT due to 0-step mitigation + * or for TD EPOCH due to contention with TDH.MEM.TRACK on TDH.VP.ENTER. + * + * When KVM requests KVM_REQ_OUTSIDE_GUEST_MODE, which has both + * KVM_REQUEST_WAIT and KVM_REQUEST_NO_ACTION set, it requires target + * vCPUs leaving fastpath so that interrupt can be enabled to ensure the + * IPIs can be delivered. Return EXIT_FASTPATH_EXIT_HANDLED instead of + * EXIT_FASTPATH_REENTER_GUEST to exit fastpath, otherwise, the + * requester may be blocked endlessly. + */ + if (unlikely(tdx_operand_busy(vp_enter_ret))) + return EXIT_FASTPATH_EXIT_HANDLED; + + return EXIT_FASTPATH_NONE; +} + +#define TDX_REGS_AVAIL_SET (BIT_ULL(VCPU_EXREG_EXIT_INFO_1) | \ + BIT_ULL(VCPU_EXREG_EXIT_INFO_2) | \ + BIT_ULL(VCPU_REGS_RAX) | \ + BIT_ULL(VCPU_REGS_RBX) | \ + BIT_ULL(VCPU_REGS_RCX) | \ + BIT_ULL(VCPU_REGS_RDX) | \ + BIT_ULL(VCPU_REGS_RBP) | \ + BIT_ULL(VCPU_REGS_RSI) | \ + BIT_ULL(VCPU_REGS_RDI) | \ + BIT_ULL(VCPU_REGS_R8) | \ + BIT_ULL(VCPU_REGS_R9) | \ + BIT_ULL(VCPU_REGS_R10) | \ + BIT_ULL(VCPU_REGS_R11) | \ + BIT_ULL(VCPU_REGS_R12) | \ + BIT_ULL(VCPU_REGS_R13) | \ + BIT_ULL(VCPU_REGS_R14) | \ + BIT_ULL(VCPU_REGS_R15)) + +static void tdx_load_host_xsave_state(struct kvm_vcpu *vcpu) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + + /* + * All TDX hosts support PKRU; but even if they didn't, + * vcpu->arch.host_pkru would be 0 and the wrpkru would be + * skipped. + */ + if (vcpu->arch.host_pkru != 0) + wrpkru(vcpu->arch.host_pkru); + + if (kvm_host.xcr0 != (kvm_tdx->xfam & kvm_caps.supported_xcr0)) + xsetbv(XCR_XFEATURE_ENABLED_MASK, kvm_host.xcr0); + + /* + * Likewise, even if a TDX hosts didn't support XSS both arms of + * the comparison would be 0 and the wrmsrl would be skipped. + */ + if (kvm_host.xss != (kvm_tdx->xfam & kvm_caps.supported_xss)) + wrmsrl(MSR_IA32_XSS, kvm_host.xss); +} + +#define TDX_DEBUGCTL_PRESERVED (DEBUGCTLMSR_BTF | \ + DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI | \ + DEBUGCTLMSR_FREEZE_IN_SMM) + +fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + struct vcpu_vt *vt = to_vt(vcpu); + + /* + * force_immediate_exit requires vCPU entering for events injection with + * an immediately exit followed. But The TDX module doesn't guarantee + * entry, it's already possible for KVM to _think_ it completely entry + * to the guest without actually having done so. + * Since KVM never needs to force an immediate exit for TDX, and can't + * do direct injection, just warn on force_immediate_exit. + */ + WARN_ON_ONCE(force_immediate_exit); + + /* + * Wait until retry of SEPT-zap-related SEAMCALL completes before + * allowing vCPU entry to avoid contention with tdh_vp_enter() and + * TDCALLs. + */ + if (unlikely(READ_ONCE(to_kvm_tdx(vcpu->kvm)->wait_for_sept_zap))) + return EXIT_FASTPATH_EXIT_HANDLED; + + trace_kvm_entry(vcpu, force_immediate_exit); + + if (pi_test_on(&vt->pi_desc)) { + apic->send_IPI_self(POSTED_INTR_VECTOR); + + if (pi_test_pir(kvm_lapic_get_reg(vcpu->arch.apic, APIC_LVTT) & + APIC_VECTOR_MASK, &vt->pi_desc)) + kvm_wait_lapic_expire(vcpu); + } + + tdx_vcpu_enter_exit(vcpu); + + if (vt->host_debugctlmsr & ~TDX_DEBUGCTL_PRESERVED) + update_debugctlmsr(vt->host_debugctlmsr); + + tdx_load_host_xsave_state(vcpu); + tdx->guest_entered = true; + + vcpu->arch.regs_avail &= TDX_REGS_AVAIL_SET; + + if (unlikely(tdx->vp_enter_ret == EXIT_REASON_EPT_MISCONFIG)) + return EXIT_FASTPATH_NONE; + + if (unlikely((tdx->vp_enter_ret & TDX_SW_ERROR) == TDX_SW_ERROR)) + return EXIT_FASTPATH_NONE; + + if (unlikely(vmx_get_exit_reason(vcpu).basic == EXIT_REASON_MCE_DURING_VMENTRY)) + kvm_machine_check(); + + trace_kvm_exit(vcpu, KVM_ISA_VMX); + + if (unlikely(tdx_failed_vmentry(vcpu))) + return EXIT_FASTPATH_NONE; + + return tdx_exit_handlers_fastpath(vcpu); +} + +void tdx_inject_nmi(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.nmi_injections; + td_management_write8(to_tdx(vcpu), TD_VCPU_PEND_NMI, 1); + /* + * From KVM's perspective, NMI injection is completed right after + * writing to PEND_NMI. KVM doesn't care whether an NMI is injected by + * the TDX module or not. + */ + vcpu->arch.nmi_injected = false; + /* + * TDX doesn't support KVM to request NMI window exit. If there is + * still a pending vNMI, KVM is not able to inject it along with the + * one pending in TDX module in a back-to-back way. Since the previous + * vNMI is still pending in TDX module, i.e. it has not been delivered + * to TDX guest yet, it's OK to collapse the pending vNMI into the + * previous one. The guest is expected to handle all the NMI sources + * when handling the first vNMI. + */ + vcpu->arch.nmi_pending = 0; +} + +static int tdx_handle_exception_nmi(struct kvm_vcpu *vcpu) +{ + u32 intr_info = vmx_get_intr_info(vcpu); + + /* + * Machine checks are handled by handle_exception_irqoff(), or by + * tdx_handle_exit() with TDX_NON_RECOVERABLE set if a #MC occurs on + * VM-Entry. NMIs are handled by tdx_vcpu_enter_exit(). + */ + if (is_nmi(intr_info) || is_machine_check(intr_info)) + return 1; + + vcpu->run->exit_reason = KVM_EXIT_EXCEPTION; + vcpu->run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK; + vcpu->run->ex.error_code = 0; + + return 0; +} + +static int complete_hypercall_exit(struct kvm_vcpu *vcpu) +{ + tdvmcall_set_return_code(vcpu, vcpu->run->hypercall.ret); + return 1; +} + +static int tdx_emulate_vmcall(struct kvm_vcpu *vcpu) +{ + kvm_rax_write(vcpu, to_tdx(vcpu)->vp_enter_args.r10); + kvm_rbx_write(vcpu, to_tdx(vcpu)->vp_enter_args.r11); + kvm_rcx_write(vcpu, to_tdx(vcpu)->vp_enter_args.r12); + kvm_rdx_write(vcpu, to_tdx(vcpu)->vp_enter_args.r13); + kvm_rsi_write(vcpu, to_tdx(vcpu)->vp_enter_args.r14); + + return __kvm_emulate_hypercall(vcpu, 0, complete_hypercall_exit); +} + +/* + * Split into chunks and check interrupt pending between chunks. This allows + * for timely injection of interrupts to prevent issues with guest lockup + * detection. + */ +#define TDX_MAP_GPA_MAX_LEN (2 * 1024 * 1024) +static void __tdx_map_gpa(struct vcpu_tdx *tdx); + +static int tdx_complete_vmcall_map_gpa(struct kvm_vcpu *vcpu) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + + if (vcpu->run->hypercall.ret) { + tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND); + tdx->vp_enter_args.r11 = tdx->map_gpa_next; + return 1; + } + + tdx->map_gpa_next += TDX_MAP_GPA_MAX_LEN; + if (tdx->map_gpa_next >= tdx->map_gpa_end) + return 1; + + /* + * Stop processing the remaining part if there is a pending interrupt, + * which could be qualified to deliver. Skip checking pending RVI for + * TDVMCALL_MAP_GPA, see comments in tdx_protected_apic_has_interrupt(). + */ + if (kvm_vcpu_has_events(vcpu)) { + tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_RETRY); + tdx->vp_enter_args.r11 = tdx->map_gpa_next; + return 1; + } + + __tdx_map_gpa(tdx); + return 0; +} + +static void __tdx_map_gpa(struct vcpu_tdx *tdx) +{ + u64 gpa = tdx->map_gpa_next; + u64 size = tdx->map_gpa_end - tdx->map_gpa_next; + + if (size > TDX_MAP_GPA_MAX_LEN) + size = TDX_MAP_GPA_MAX_LEN; + + tdx->vcpu.run->exit_reason = KVM_EXIT_HYPERCALL; + tdx->vcpu.run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + /* + * In principle this should have been -KVM_ENOSYS, but userspace (QEMU <=9.2) + * assumed that vcpu->run->hypercall.ret is never changed by KVM and thus that + * it was always zero on KVM_EXIT_HYPERCALL. Since KVM is now overwriting + * vcpu->run->hypercall.ret, ensuring that it is zero to not break QEMU. + */ + tdx->vcpu.run->hypercall.ret = 0; + tdx->vcpu.run->hypercall.args[0] = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(tdx->vcpu.kvm)); + tdx->vcpu.run->hypercall.args[1] = size / PAGE_SIZE; + tdx->vcpu.run->hypercall.args[2] = vt_is_tdx_private_gpa(tdx->vcpu.kvm, gpa) ? + KVM_MAP_GPA_RANGE_ENCRYPTED : + KVM_MAP_GPA_RANGE_DECRYPTED; + tdx->vcpu.run->hypercall.flags = KVM_EXIT_HYPERCALL_LONG_MODE; + + tdx->vcpu.arch.complete_userspace_io = tdx_complete_vmcall_map_gpa; +} + +static int tdx_map_gpa(struct kvm_vcpu *vcpu) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + u64 gpa = tdx->vp_enter_args.r12; + u64 size = tdx->vp_enter_args.r13; + u64 ret; + + /* + * Converting TDVMCALL_MAP_GPA to KVM_HC_MAP_GPA_RANGE requires + * userspace to enable KVM_CAP_EXIT_HYPERCALL with KVM_HC_MAP_GPA_RANGE + * bit set. If not, the error code is not defined in GHCI for TDX, use + * TDVMCALL_STATUS_INVALID_OPERAND for this case. + */ + if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) { + ret = TDVMCALL_STATUS_INVALID_OPERAND; + goto error; + } + + if (gpa + size <= gpa || !kvm_vcpu_is_legal_gpa(vcpu, gpa) || + !kvm_vcpu_is_legal_gpa(vcpu, gpa + size - 1) || + (vt_is_tdx_private_gpa(vcpu->kvm, gpa) != + vt_is_tdx_private_gpa(vcpu->kvm, gpa + size - 1))) { + ret = TDVMCALL_STATUS_INVALID_OPERAND; + goto error; + } + + if (!PAGE_ALIGNED(gpa) || !PAGE_ALIGNED(size)) { + ret = TDVMCALL_STATUS_ALIGN_ERROR; + goto error; + } + + tdx->map_gpa_end = gpa + size; + tdx->map_gpa_next = gpa; + + __tdx_map_gpa(tdx); + return 0; + +error: + tdvmcall_set_return_code(vcpu, ret); + tdx->vp_enter_args.r11 = gpa; + return 1; +} + +static int tdx_report_fatal_error(struct kvm_vcpu *vcpu) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + u64 *regs = vcpu->run->system_event.data; + u64 *module_regs = &tdx->vp_enter_args.r8; + int index = VCPU_REGS_RAX; + + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + vcpu->run->system_event.type = KVM_SYSTEM_EVENT_TDX_FATAL; + vcpu->run->system_event.ndata = 16; + + /* Dump 16 general-purpose registers to userspace in ascending order. */ + regs[index++] = tdx->vp_enter_ret; + regs[index++] = tdx->vp_enter_args.rcx; + regs[index++] = tdx->vp_enter_args.rdx; + regs[index++] = tdx->vp_enter_args.rbx; + regs[index++] = 0; + regs[index++] = 0; + regs[index++] = tdx->vp_enter_args.rsi; + regs[index] = tdx->vp_enter_args.rdi; + for (index = 0; index < 8; index++) + regs[VCPU_REGS_R8 + index] = module_regs[index]; + + return 0; +} + +static int tdx_emulate_cpuid(struct kvm_vcpu *vcpu) +{ + u32 eax, ebx, ecx, edx; + struct vcpu_tdx *tdx = to_tdx(vcpu); + + /* EAX and ECX for cpuid is stored in R12 and R13. */ + eax = tdx->vp_enter_args.r12; + ecx = tdx->vp_enter_args.r13; + + kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, false); + + tdx->vp_enter_args.r12 = eax; + tdx->vp_enter_args.r13 = ebx; + tdx->vp_enter_args.r14 = ecx; + tdx->vp_enter_args.r15 = edx; + + return 1; +} + +static int tdx_complete_pio_out(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pio.count = 0; + return 1; +} + +static int tdx_complete_pio_in(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + unsigned long val = 0; + int ret; + + ret = ctxt->ops->pio_in_emulated(ctxt, vcpu->arch.pio.size, + vcpu->arch.pio.port, &val, 1); + + WARN_ON_ONCE(!ret); + + tdvmcall_set_return_val(vcpu, val); + + return 1; +} + +static int tdx_emulate_io(struct kvm_vcpu *vcpu) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + unsigned long val = 0; + unsigned int port; + u64 size, write; + int ret; + + ++vcpu->stat.io_exits; + + size = tdx->vp_enter_args.r12; + write = tdx->vp_enter_args.r13; + port = tdx->vp_enter_args.r14; + + if ((write != 0 && write != 1) || (size != 1 && size != 2 && size != 4)) { + tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND); + return 1; + } + + if (write) { + val = tdx->vp_enter_args.r15; + ret = ctxt->ops->pio_out_emulated(ctxt, size, port, &val, 1); + } else { + ret = ctxt->ops->pio_in_emulated(ctxt, size, port, &val, 1); + } + + if (!ret) + vcpu->arch.complete_userspace_io = write ? tdx_complete_pio_out : + tdx_complete_pio_in; + else if (!write) + tdvmcall_set_return_val(vcpu, val); + + return ret; +} + +static int tdx_complete_mmio_read(struct kvm_vcpu *vcpu) +{ + unsigned long val = 0; + gpa_t gpa; + int size; + + gpa = vcpu->mmio_fragments[0].gpa; + size = vcpu->mmio_fragments[0].len; + + memcpy(&val, vcpu->run->mmio.data, size); + tdvmcall_set_return_val(vcpu, val); + trace_kvm_mmio(KVM_TRACE_MMIO_READ, size, gpa, &val); + return 1; +} + +static inline int tdx_mmio_write(struct kvm_vcpu *vcpu, gpa_t gpa, int size, + unsigned long val) +{ + if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { + trace_kvm_fast_mmio(gpa); + return 0; + } + + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, size, gpa, &val); + if (kvm_io_bus_write(vcpu, KVM_MMIO_BUS, gpa, size, &val)) + return -EOPNOTSUPP; + + return 0; +} + +static inline int tdx_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, int size) +{ + unsigned long val; + + if (kvm_io_bus_read(vcpu, KVM_MMIO_BUS, gpa, size, &val)) + return -EOPNOTSUPP; + + tdvmcall_set_return_val(vcpu, val); + trace_kvm_mmio(KVM_TRACE_MMIO_READ, size, gpa, &val); + return 0; +} + +static int tdx_emulate_mmio(struct kvm_vcpu *vcpu) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + int size, write, r; + unsigned long val; + gpa_t gpa; + + size = tdx->vp_enter_args.r12; + write = tdx->vp_enter_args.r13; + gpa = tdx->vp_enter_args.r14; + val = write ? tdx->vp_enter_args.r15 : 0; + + if (size != 1 && size != 2 && size != 4 && size != 8) + goto error; + if (write != 0 && write != 1) + goto error; + + /* + * TDG.VP.VMCALL<MMIO> allows only shared GPA, it makes no sense to + * do MMIO emulation for private GPA. + */ + if (vt_is_tdx_private_gpa(vcpu->kvm, gpa) || + vt_is_tdx_private_gpa(vcpu->kvm, gpa + size - 1)) + goto error; + + gpa = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm)); + + if (write) + r = tdx_mmio_write(vcpu, gpa, size, val); + else + r = tdx_mmio_read(vcpu, gpa, size); + if (!r) + /* Kernel completed device emulation. */ + return 1; + + /* Request the device emulation to userspace device model. */ + vcpu->mmio_is_write = write; + if (!write) + vcpu->arch.complete_userspace_io = tdx_complete_mmio_read; + + vcpu->run->mmio.phys_addr = gpa; + vcpu->run->mmio.len = size; + vcpu->run->mmio.is_write = write; + vcpu->run->exit_reason = KVM_EXIT_MMIO; + + if (write) { + memcpy(vcpu->run->mmio.data, &val, size); + } else { + vcpu->mmio_fragments[0].gpa = gpa; + vcpu->mmio_fragments[0].len = size; + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, size, gpa, NULL); + } + return 0; + +error: + tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND); + return 1; +} + +static int tdx_get_td_vm_call_info(struct kvm_vcpu *vcpu) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + + if (tdx->vp_enter_args.r12) + tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND); + else { + tdx->vp_enter_args.r11 = 0; + tdx->vp_enter_args.r13 = 0; + tdx->vp_enter_args.r14 = 0; + } + return 1; +} + +static int handle_tdvmcall(struct kvm_vcpu *vcpu) +{ + switch (tdvmcall_leaf(vcpu)) { + case TDVMCALL_MAP_GPA: + return tdx_map_gpa(vcpu); + case TDVMCALL_REPORT_FATAL_ERROR: + return tdx_report_fatal_error(vcpu); + case TDVMCALL_GET_TD_VM_CALL_INFO: + return tdx_get_td_vm_call_info(vcpu); + default: + break; + } + + tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND); + return 1; +} + +void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level) +{ + u64 shared_bit = (pgd_level == 5) ? TDX_SHARED_BIT_PWL_5 : + TDX_SHARED_BIT_PWL_4; + + if (KVM_BUG_ON(shared_bit != kvm_gfn_direct_bits(vcpu->kvm), vcpu->kvm)) + return; + + td_vmcs_write64(to_tdx(vcpu), SHARED_EPT_POINTER, root_hpa); +} + +static void tdx_unpin(struct kvm *kvm, struct page *page) +{ + put_page(page); +} + +static int tdx_mem_page_aug(struct kvm *kvm, gfn_t gfn, + enum pg_level level, struct page *page) +{ + int tdx_level = pg_level_to_tdx_sept_level(level); + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + gpa_t gpa = gfn_to_gpa(gfn); + u64 entry, level_state; + u64 err; + + err = tdh_mem_page_aug(&kvm_tdx->td, gpa, tdx_level, page, &entry, &level_state); + if (unlikely(tdx_operand_busy(err))) { + tdx_unpin(kvm, page); + return -EBUSY; + } + + if (KVM_BUG_ON(err, kvm)) { + pr_tdx_error_2(TDH_MEM_PAGE_AUG, err, entry, level_state); + tdx_unpin(kvm, page); + return -EIO; + } + + return 0; +} + +/* + * KVM_TDX_INIT_MEM_REGION calls kvm_gmem_populate() to map guest pages; the + * callback tdx_gmem_post_populate() then maps pages into private memory. + * through the a seamcall TDH.MEM.PAGE.ADD(). The SEAMCALL also requires the + * private EPT structures for the page to have been built before, which is + * done via kvm_tdp_map_page(). nr_premapped counts the number of pages that + * were added to the EPT structures but not added with TDH.MEM.PAGE.ADD(). + * The counter has to be zero on KVM_TDX_FINALIZE_VM, to ensure that there + * are no half-initialized shared EPT pages. + */ +static int tdx_mem_page_record_premap_cnt(struct kvm *kvm, gfn_t gfn, + enum pg_level level, kvm_pfn_t pfn) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + + if (KVM_BUG_ON(kvm->arch.pre_fault_allowed, kvm)) + return -EINVAL; + + /* nr_premapped will be decreased when tdh_mem_page_add() is called. */ + atomic64_inc(&kvm_tdx->nr_premapped); + return 0; +} + +int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn, + enum pg_level level, kvm_pfn_t pfn) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + struct page *page = pfn_to_page(pfn); + + /* TODO: handle large pages. */ + if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm)) + return -EINVAL; + + /* + * Because guest_memfd doesn't support page migration with + * a_ops->migrate_folio (yet), no callback is triggered for KVM on page + * migration. Until guest_memfd supports page migration, prevent page + * migration. + * TODO: Once guest_memfd introduces callback on page migration, + * implement it and remove get_page/put_page(). + */ + get_page(page); + + /* + * Read 'pre_fault_allowed' before 'kvm_tdx->state'; see matching + * barrier in tdx_td_finalize(). + */ + smp_rmb(); + if (likely(kvm_tdx->state == TD_STATE_RUNNABLE)) + return tdx_mem_page_aug(kvm, gfn, level, page); + + return tdx_mem_page_record_premap_cnt(kvm, gfn, level, pfn); +} + +static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn, + enum pg_level level, struct page *page) +{ + int tdx_level = pg_level_to_tdx_sept_level(level); + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + gpa_t gpa = gfn_to_gpa(gfn); + u64 err, entry, level_state; + + /* TODO: handle large pages. */ + if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm)) + return -EINVAL; + + if (KVM_BUG_ON(!is_hkid_assigned(kvm_tdx), kvm)) + return -EINVAL; + + /* + * When zapping private page, write lock is held. So no race condition + * with other vcpu sept operation. + * Race with TDH.VP.ENTER due to (0-step mitigation) and Guest TDCALLs. + */ + err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry, + &level_state); + + if (unlikely(tdx_operand_busy(err))) { + /* + * The second retry is expected to succeed after kicking off all + * other vCPUs and prevent them from invoking TDH.VP.ENTER. + */ + tdx_no_vcpus_enter_start(kvm); + err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry, + &level_state); + tdx_no_vcpus_enter_stop(kvm); + } + + if (KVM_BUG_ON(err, kvm)) { + pr_tdx_error_2(TDH_MEM_PAGE_REMOVE, err, entry, level_state); + return -EIO; + } + + err = tdh_phymem_page_wbinvd_hkid((u16)kvm_tdx->hkid, page); + + if (KVM_BUG_ON(err, kvm)) { + pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err); + return -EIO; + } + tdx_clear_page(page); + tdx_unpin(kvm, page); + return 0; +} + +int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn, + enum pg_level level, void *private_spt) +{ + int tdx_level = pg_level_to_tdx_sept_level(level); + gpa_t gpa = gfn_to_gpa(gfn); + struct page *page = virt_to_page(private_spt); + u64 err, entry, level_state; + + err = tdh_mem_sept_add(&to_kvm_tdx(kvm)->td, gpa, tdx_level, page, &entry, + &level_state); + if (unlikely(tdx_operand_busy(err))) + return -EBUSY; + + if (KVM_BUG_ON(err, kvm)) { + pr_tdx_error_2(TDH_MEM_SEPT_ADD, err, entry, level_state); + return -EIO; + } + + return 0; +} + +/* + * Check if the error returned from a SEPT zap SEAMCALL is due to that a page is + * mapped by KVM_TDX_INIT_MEM_REGION without tdh_mem_page_add() being called + * successfully. + * + * Since tdh_mem_sept_add() must have been invoked successfully before a + * non-leaf entry present in the mirrored page table, the SEPT ZAP related + * SEAMCALLs should not encounter err TDX_EPT_WALK_FAILED. They should instead + * find TDX_EPT_ENTRY_STATE_INCORRECT due to an empty leaf entry found in the + * SEPT. + * + * Further check if the returned entry from SEPT walking is with RWX permissions + * to filter out anything unexpected. + * + * Note: @level is pg_level, not the tdx_level. The tdx_level extracted from + * level_state returned from a SEAMCALL error is the same as that passed into + * the SEAMCALL. + */ +static int tdx_is_sept_zap_err_due_to_premap(struct kvm_tdx *kvm_tdx, u64 err, + u64 entry, int level) +{ + if (!err || kvm_tdx->state == TD_STATE_RUNNABLE) + return false; + + if (err != (TDX_EPT_ENTRY_STATE_INCORRECT | TDX_OPERAND_ID_RCX)) + return false; + + if ((is_last_spte(entry, level) && (entry & VMX_EPT_RWX_MASK))) + return false; + + return true; +} + +static int tdx_sept_zap_private_spte(struct kvm *kvm, gfn_t gfn, + enum pg_level level, struct page *page) +{ + int tdx_level = pg_level_to_tdx_sept_level(level); + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + gpa_t gpa = gfn_to_gpa(gfn) & KVM_HPAGE_MASK(level); + u64 err, entry, level_state; + + /* For now large page isn't supported yet. */ + WARN_ON_ONCE(level != PG_LEVEL_4K); + + err = tdh_mem_range_block(&kvm_tdx->td, gpa, tdx_level, &entry, &level_state); + + if (unlikely(tdx_operand_busy(err))) { + /* After no vCPUs enter, the second retry is expected to succeed */ + tdx_no_vcpus_enter_start(kvm); + err = tdh_mem_range_block(&kvm_tdx->td, gpa, tdx_level, &entry, &level_state); + tdx_no_vcpus_enter_stop(kvm); + } + if (tdx_is_sept_zap_err_due_to_premap(kvm_tdx, err, entry, level) && + !KVM_BUG_ON(!atomic64_read(&kvm_tdx->nr_premapped), kvm)) { + atomic64_dec(&kvm_tdx->nr_premapped); + tdx_unpin(kvm, page); + return 0; + } + + if (KVM_BUG_ON(err, kvm)) { + pr_tdx_error_2(TDH_MEM_RANGE_BLOCK, err, entry, level_state); + return -EIO; + } + return 1; +} + +/* + * Ensure shared and private EPTs to be flushed on all vCPUs. + * tdh_mem_track() is the only caller that increases TD epoch. An increase in + * the TD epoch (e.g., to value "N + 1") is successful only if no vCPUs are + * running in guest mode with the value "N - 1". + * + * A successful execution of tdh_mem_track() ensures that vCPUs can only run in + * guest mode with TD epoch value "N" if no TD exit occurs after the TD epoch + * being increased to "N + 1". + * + * Kicking off all vCPUs after that further results in no vCPUs can run in guest + * mode with TD epoch value "N", which unblocks the next tdh_mem_track() (e.g. + * to increase TD epoch to "N + 2"). + * + * TDX module will flush EPT on the next TD enter and make vCPUs to run in + * guest mode with TD epoch value "N + 1". + * + * kvm_make_all_cpus_request() guarantees all vCPUs are out of guest mode by + * waiting empty IPI handler ack_kick(). + * + * No action is required to the vCPUs being kicked off since the kicking off + * occurs certainly after TD epoch increment and before the next + * tdh_mem_track(). + */ +static void tdx_track(struct kvm *kvm) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + u64 err; + + /* If TD isn't finalized, it's before any vcpu running. */ + if (unlikely(kvm_tdx->state != TD_STATE_RUNNABLE)) + return; + + lockdep_assert_held_write(&kvm->mmu_lock); + + err = tdh_mem_track(&kvm_tdx->td); + if (unlikely(tdx_operand_busy(err))) { + /* After no vCPUs enter, the second retry is expected to succeed */ + tdx_no_vcpus_enter_start(kvm); + err = tdh_mem_track(&kvm_tdx->td); + tdx_no_vcpus_enter_stop(kvm); + } + + if (KVM_BUG_ON(err, kvm)) + pr_tdx_error(TDH_MEM_TRACK, err); + + kvm_make_all_cpus_request(kvm, KVM_REQ_OUTSIDE_GUEST_MODE); +} + +int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn, + enum pg_level level, void *private_spt) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + + /* + * free_external_spt() is only called after hkid is freed when TD is + * tearing down. + * KVM doesn't (yet) zap page table pages in mirror page table while + * TD is active, though guest pages mapped in mirror page table could be + * zapped during TD is active, e.g. for shared <-> private conversion + * and slot move/deletion. + */ + if (KVM_BUG_ON(is_hkid_assigned(kvm_tdx), kvm)) + return -EINVAL; + + /* + * The HKID assigned to this TD was already freed and cache was + * already flushed. We don't have to flush again. + */ + return tdx_reclaim_page(virt_to_page(private_spt)); +} + +int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, + enum pg_level level, kvm_pfn_t pfn) +{ + struct page *page = pfn_to_page(pfn); + int ret; + + /* + * HKID is released after all private pages have been removed, and set + * before any might be populated. Warn if zapping is attempted when + * there can't be anything populated in the private EPT. + */ + if (KVM_BUG_ON(!is_hkid_assigned(to_kvm_tdx(kvm)), kvm)) + return -EINVAL; + + ret = tdx_sept_zap_private_spte(kvm, gfn, level, page); + if (ret <= 0) + return ret; + + /* + * TDX requires TLB tracking before dropping private page. Do + * it here, although it is also done later. + */ + tdx_track(kvm); + + return tdx_sept_drop_private_spte(kvm, gfn, level, page); +} + +void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) +{ + struct kvm_vcpu *vcpu = apic->vcpu; + struct vcpu_tdx *tdx = to_tdx(vcpu); + + /* TDX supports only posted interrupt. No lapic emulation. */ + __vmx_deliver_posted_interrupt(vcpu, &tdx->vt.pi_desc, vector); + + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, trig_mode, vector); +} + +static inline bool tdx_is_sept_violation_unexpected_pending(struct kvm_vcpu *vcpu) +{ + u64 eeq_type = to_tdx(vcpu)->ext_exit_qualification & TDX_EXT_EXIT_QUAL_TYPE_MASK; + u64 eq = vmx_get_exit_qual(vcpu); + + if (eeq_type != TDX_EXT_EXIT_QUAL_TYPE_PENDING_EPT_VIOLATION) + return false; + + return !(eq & EPT_VIOLATION_PROT_MASK) && !(eq & EPT_VIOLATION_EXEC_FOR_RING3_LIN); +} + +static int tdx_handle_ept_violation(struct kvm_vcpu *vcpu) +{ + unsigned long exit_qual; + gpa_t gpa = to_tdx(vcpu)->exit_gpa; + bool local_retry = false; + int ret; + + if (vt_is_tdx_private_gpa(vcpu->kvm, gpa)) { + if (tdx_is_sept_violation_unexpected_pending(vcpu)) { + pr_warn("Guest access before accepting 0x%llx on vCPU %d\n", + gpa, vcpu->vcpu_id); + kvm_vm_dead(vcpu->kvm); + return -EIO; + } + /* + * Always treat SEPT violations as write faults. Ignore the + * EXIT_QUALIFICATION reported by TDX-SEAM for SEPT violations. + * TD private pages are always RWX in the SEPT tables, + * i.e. they're always mapped writable. Just as importantly, + * treating SEPT violations as write faults is necessary to + * avoid COW allocations, which will cause TDAUGPAGE failures + * due to aliasing a single HPA to multiple GPAs. + */ + exit_qual = EPT_VIOLATION_ACC_WRITE; + + /* Only private GPA triggers zero-step mitigation */ + local_retry = true; + } else { + exit_qual = vmx_get_exit_qual(vcpu); + /* + * EPT violation due to instruction fetch should never be + * triggered from shared memory in TDX guest. If such EPT + * violation occurs, treat it as broken hardware. + */ + if (KVM_BUG_ON(exit_qual & EPT_VIOLATION_ACC_INSTR, vcpu->kvm)) + return -EIO; + } + + trace_kvm_page_fault(vcpu, gpa, exit_qual); + + /* + * To minimize TDH.VP.ENTER invocations, retry locally for private GPA + * mapping in TDX. + * + * KVM may return RET_PF_RETRY for private GPA due to + * - contentions when atomically updating SPTEs of the mirror page table + * - in-progress GFN invalidation or memslot removal. + * - TDX_OPERAND_BUSY error from TDH.MEM.PAGE.AUG or TDH.MEM.SEPT.ADD, + * caused by contentions with TDH.VP.ENTER (with zero-step mitigation) + * or certain TDCALLs. + * + * If TDH.VP.ENTER is invoked more times than the threshold set by the + * TDX module before KVM resolves the private GPA mapping, the TDX + * module will activate zero-step mitigation during TDH.VP.ENTER. This + * process acquires an SEPT tree lock in the TDX module, leading to + * further contentions with TDH.MEM.PAGE.AUG or TDH.MEM.SEPT.ADD + * operations on other vCPUs. + * + * Breaking out of local retries for kvm_vcpu_has_events() is for + * interrupt injection. kvm_vcpu_has_events() should not see pending + * events for TDX. Since KVM can't determine if IRQs (or NMIs) are + * blocked by TDs, false positives are inevitable i.e., KVM may re-enter + * the guest even if the IRQ/NMI can't be delivered. + * + * Note: even without breaking out of local retries, zero-step + * mitigation may still occur due to + * - invoking of TDH.VP.ENTER after KVM_EXIT_MEMORY_FAULT, + * - a single RIP causing EPT violations for more GFNs than the + * threshold count. + * This is safe, as triggering zero-step mitigation only introduces + * contentions to page installation SEAMCALLs on other vCPUs, which will + * handle retries locally in their EPT violation handlers. + */ + while (1) { + ret = __vmx_handle_ept_violation(vcpu, gpa, exit_qual); + + if (ret != RET_PF_RETRY || !local_retry) + break; + + if (kvm_vcpu_has_events(vcpu) || signal_pending(current)) + break; + + if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) { + ret = -EIO; + break; + } + + cond_resched(); + } + return ret; +} + +int tdx_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) +{ + if (err) { + tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND); + return 1; + } + + if (vmx_get_exit_reason(vcpu).basic == EXIT_REASON_MSR_READ) + tdvmcall_set_return_val(vcpu, kvm_read_edx_eax(vcpu)); + + return 1; +} + + +int tdx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t fastpath) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + u64 vp_enter_ret = tdx->vp_enter_ret; + union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu); + + if (fastpath != EXIT_FASTPATH_NONE) + return 1; + + if (unlikely(vp_enter_ret == EXIT_REASON_EPT_MISCONFIG)) { + KVM_BUG_ON(1, vcpu->kvm); + return -EIO; + } + + /* + * Handle TDX SW errors, including TDX_SEAMCALL_UD, TDX_SEAMCALL_GP and + * TDX_SEAMCALL_VMFAILINVALID. + */ + if (unlikely((vp_enter_ret & TDX_SW_ERROR) == TDX_SW_ERROR)) { + KVM_BUG_ON(!kvm_rebooting, vcpu->kvm); + goto unhandled_exit; + } + + if (unlikely(tdx_failed_vmentry(vcpu))) { + /* + * If the guest state is protected, that means off-TD debug is + * not enabled, TDX_NON_RECOVERABLE must be set. + */ + WARN_ON_ONCE(vcpu->arch.guest_state_protected && + !(vp_enter_ret & TDX_NON_RECOVERABLE)); + vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; + vcpu->run->fail_entry.hardware_entry_failure_reason = exit_reason.full; + vcpu->run->fail_entry.cpu = vcpu->arch.last_vmentry_cpu; + return 0; + } + + if (unlikely(vp_enter_ret & (TDX_ERROR | TDX_NON_RECOVERABLE)) && + exit_reason.basic != EXIT_REASON_TRIPLE_FAULT) { + kvm_pr_unimpl("TD vp_enter_ret 0x%llx\n", vp_enter_ret); + goto unhandled_exit; + } + + WARN_ON_ONCE(exit_reason.basic != EXIT_REASON_TRIPLE_FAULT && + (vp_enter_ret & TDX_SEAMCALL_STATUS_MASK) != TDX_SUCCESS); + + switch (exit_reason.basic) { + case EXIT_REASON_TRIPLE_FAULT: + vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; + vcpu->mmio_needed = 0; + return 0; + case EXIT_REASON_EXCEPTION_NMI: + return tdx_handle_exception_nmi(vcpu); + case EXIT_REASON_EXTERNAL_INTERRUPT: + ++vcpu->stat.irq_exits; + return 1; + case EXIT_REASON_CPUID: + return tdx_emulate_cpuid(vcpu); + case EXIT_REASON_HLT: + return kvm_emulate_halt_noskip(vcpu); + case EXIT_REASON_TDCALL: + return handle_tdvmcall(vcpu); + case EXIT_REASON_VMCALL: + return tdx_emulate_vmcall(vcpu); + case EXIT_REASON_IO_INSTRUCTION: + return tdx_emulate_io(vcpu); + case EXIT_REASON_MSR_READ: + kvm_rcx_write(vcpu, tdx->vp_enter_args.r12); + return kvm_emulate_rdmsr(vcpu); + case EXIT_REASON_MSR_WRITE: + kvm_rcx_write(vcpu, tdx->vp_enter_args.r12); + kvm_rax_write(vcpu, tdx->vp_enter_args.r13 & -1u); + kvm_rdx_write(vcpu, tdx->vp_enter_args.r13 >> 32); + return kvm_emulate_wrmsr(vcpu); + case EXIT_REASON_EPT_MISCONFIG: + return tdx_emulate_mmio(vcpu); + case EXIT_REASON_EPT_VIOLATION: + return tdx_handle_ept_violation(vcpu); + case EXIT_REASON_OTHER_SMI: + /* + * Unlike VMX, SMI in SEAM non-root mode (i.e. when + * TD guest vCPU is running) will cause VM exit to TDX module, + * then SEAMRET to KVM. Once it exits to KVM, SMI is delivered + * and handled by kernel handler right away. + * + * The Other SMI exit can also be caused by the SEAM non-root + * machine check delivered via Machine Check System Management + * Interrupt (MSMI), but it has already been handled by the + * kernel machine check handler, i.e., the memory page has been + * marked as poisoned and it won't be freed to the free list + * when the TDX guest is terminated (the TDX module marks the + * guest as dead and prevent it from further running when + * machine check happens in SEAM non-root). + * + * - A MSMI will not reach here, it's handled as non_recoverable + * case above. + * - If it's not an MSMI, no need to do anything here. + */ + return 1; + default: + break; + } + +unhandled_exit: + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 2; + vcpu->run->internal.data[0] = vp_enter_ret; + vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + return 0; +} + +void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + + *reason = tdx->vt.exit_reason.full; + if (*reason != -1u) { + *info1 = vmx_get_exit_qual(vcpu); + *info2 = tdx->ext_exit_qualification; + *intr_info = vmx_get_intr_info(vcpu); + } else { + *info1 = 0; + *info2 = 0; + *intr_info = 0; + } + + *error_code = 0; +} + +bool tdx_has_emulated_msr(u32 index) +{ + switch (index) { + case MSR_IA32_UCODE_REV: + case MSR_IA32_ARCH_CAPABILITIES: + case MSR_IA32_POWER_CTL: + case MSR_IA32_CR_PAT: + case MSR_MTRRcap: + case MTRRphysBase_MSR(0) ... MSR_MTRRfix4K_F8000: + case MSR_MTRRdefType: + case MSR_IA32_TSC_DEADLINE: + case MSR_IA32_MISC_ENABLE: + case MSR_PLATFORM_INFO: + case MSR_MISC_FEATURES_ENABLES: + case MSR_IA32_APICBASE: + case MSR_EFER: + case MSR_IA32_FEAT_CTL: + case MSR_IA32_MCG_CAP: + case MSR_IA32_MCG_STATUS: + case MSR_IA32_MCG_CTL: + case MSR_IA32_MCG_EXT_CTL: + case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: + case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: + /* MSR_IA32_MCx_{CTL, STATUS, ADDR, MISC, CTL2} */ + case MSR_KVM_POLL_CONTROL: + return true; + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: + /* + * x2APIC registers that are virtualized by the CPU can't be + * emulated, KVM doesn't have access to the virtual APIC page. + */ + switch (index) { + case X2APIC_MSR(APIC_TASKPRI): + case X2APIC_MSR(APIC_PROCPRI): + case X2APIC_MSR(APIC_EOI): + case X2APIC_MSR(APIC_ISR) ... X2APIC_MSR(APIC_ISR + APIC_ISR_NR): + case X2APIC_MSR(APIC_TMR) ... X2APIC_MSR(APIC_TMR + APIC_ISR_NR): + case X2APIC_MSR(APIC_IRR) ... X2APIC_MSR(APIC_IRR + APIC_ISR_NR): + return false; + default: + return true; + } + default: + return false; + } +} + +static bool tdx_is_read_only_msr(u32 index) +{ + return index == MSR_IA32_APICBASE || index == MSR_EFER || + index == MSR_IA32_FEAT_CTL; +} + +int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) +{ + switch (msr->index) { + case MSR_IA32_FEAT_CTL: + /* + * MCE and MCA are advertised via cpuid. Guest kernel could + * check if LMCE is enabled or not. + */ + msr->data = FEAT_CTL_LOCKED; + if (vcpu->arch.mcg_cap & MCG_LMCE_P) + msr->data |= FEAT_CTL_LMCE_ENABLED; + return 0; + case MSR_IA32_MCG_EXT_CTL: + if (!msr->host_initiated && !(vcpu->arch.mcg_cap & MCG_LMCE_P)) + return 1; + msr->data = vcpu->arch.mcg_ext_ctl; + return 0; + default: + if (!tdx_has_emulated_msr(msr->index)) + return 1; + + return kvm_get_msr_common(vcpu, msr); + } +} + +int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) +{ + switch (msr->index) { + case MSR_IA32_MCG_EXT_CTL: + if ((!msr->host_initiated && !(vcpu->arch.mcg_cap & MCG_LMCE_P)) || + (msr->data & ~MCG_EXT_CTL_LMCE_EN)) + return 1; + vcpu->arch.mcg_ext_ctl = msr->data; + return 0; + default: + if (tdx_is_read_only_msr(msr->index)) + return 1; + + if (!tdx_has_emulated_msr(msr->index)) + return 1; + + return kvm_set_msr_common(vcpu, msr); + } +} + +static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd) +{ + const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf; + struct kvm_tdx_capabilities __user *user_caps; + struct kvm_tdx_capabilities *caps = NULL; + int ret = 0; + + /* flags is reserved for future use */ + if (cmd->flags) + return -EINVAL; + + caps = kmalloc(sizeof(*caps) + + sizeof(struct kvm_cpuid_entry2) * td_conf->num_cpuid_config, + GFP_KERNEL); + if (!caps) + return -ENOMEM; + + user_caps = u64_to_user_ptr(cmd->data); + if (copy_from_user(caps, user_caps, sizeof(*caps))) { + ret = -EFAULT; + goto out; + } + + if (caps->cpuid.nent < td_conf->num_cpuid_config) { + ret = -E2BIG; + goto out; + } + + ret = init_kvm_tdx_caps(td_conf, caps); + if (ret) + goto out; + + if (copy_to_user(user_caps, caps, sizeof(*caps))) { + ret = -EFAULT; + goto out; + } + + if (copy_to_user(user_caps->cpuid.entries, caps->cpuid.entries, + caps->cpuid.nent * + sizeof(caps->cpuid.entries[0]))) + ret = -EFAULT; + +out: + /* kfree() accepts NULL. */ + kfree(caps); + return ret; +} + +/* + * KVM reports guest physical address in CPUID.0x800000008.EAX[23:16], which is + * similar to TDX's GPAW. Use this field as the interface for userspace to + * configure the GPAW and EPT level for TDs. + * + * Only values 48 and 52 are supported. Value 52 means GPAW-52 and EPT level + * 5, Value 48 means GPAW-48 and EPT level 4. For value 48, GPAW-48 is always + * supported. Value 52 is only supported when the platform supports 5 level + * EPT. + */ +static int setup_tdparams_eptp_controls(struct kvm_cpuid2 *cpuid, + struct td_params *td_params) +{ + const struct kvm_cpuid_entry2 *entry; + int guest_pa; + + entry = kvm_find_cpuid_entry2(cpuid->entries, cpuid->nent, 0x80000008, 0); + if (!entry) + return -EINVAL; + + guest_pa = tdx_get_guest_phys_addr_bits(entry->eax); + + if (guest_pa != 48 && guest_pa != 52) + return -EINVAL; + + if (guest_pa == 52 && !cpu_has_vmx_ept_5levels()) + return -EINVAL; + + td_params->eptp_controls = VMX_EPTP_MT_WB; + if (guest_pa == 52) { + td_params->eptp_controls |= VMX_EPTP_PWL_5; + td_params->config_flags |= TDX_CONFIG_FLAGS_MAX_GPAW; + } else { + td_params->eptp_controls |= VMX_EPTP_PWL_4; + } + + return 0; +} + +static int setup_tdparams_cpuids(struct kvm_cpuid2 *cpuid, + struct td_params *td_params) +{ + const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf; + const struct kvm_cpuid_entry2 *entry; + struct tdx_cpuid_value *value; + int i, copy_cnt = 0; + + /* + * td_params.cpuid_values: The number and the order of cpuid_value must + * be same to the one of struct tdsysinfo.{num_cpuid_config, cpuid_configs} + * It's assumed that td_params was zeroed. + */ + for (i = 0; i < td_conf->num_cpuid_config; i++) { + struct kvm_cpuid_entry2 tmp; + + td_init_cpuid_entry2(&tmp, i); + + entry = kvm_find_cpuid_entry2(cpuid->entries, cpuid->nent, + tmp.function, tmp.index); + if (!entry) + continue; + + if (tdx_unsupported_cpuid(entry)) + return -EINVAL; + + copy_cnt++; + + value = &td_params->cpuid_values[i]; + value->eax = entry->eax; + value->ebx = entry->ebx; + value->ecx = entry->ecx; + value->edx = entry->edx; + + /* + * TDX module does not accept nonzero bits 16..23 for the + * CPUID[0x80000008].EAX, see setup_tdparams_eptp_controls(). + */ + if (tmp.function == 0x80000008) + value->eax = tdx_set_guest_phys_addr_bits(value->eax, 0); + } + + /* + * Rely on the TDX module to reject invalid configuration, but it can't + * check of leafs that don't have a proper slot in td_params->cpuid_values + * to stick then. So fail if there were entries that didn't get copied to + * td_params. + */ + if (copy_cnt != cpuid->nent) + return -EINVAL; + + return 0; +} + +static int setup_tdparams(struct kvm *kvm, struct td_params *td_params, + struct kvm_tdx_init_vm *init_vm) +{ + const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf; + struct kvm_cpuid2 *cpuid = &init_vm->cpuid; + int ret; + + if (kvm->created_vcpus) + return -EBUSY; + + if (init_vm->attributes & ~tdx_get_supported_attrs(td_conf)) + return -EINVAL; + + if (init_vm->xfam & ~tdx_get_supported_xfam(td_conf)) + return -EINVAL; + + td_params->max_vcpus = kvm->max_vcpus; + td_params->attributes = init_vm->attributes | td_conf->attributes_fixed1; + td_params->xfam = init_vm->xfam | td_conf->xfam_fixed1; + + td_params->config_flags = TDX_CONFIG_FLAGS_NO_RBP_MOD; + td_params->tsc_frequency = TDX_TSC_KHZ_TO_25MHZ(kvm->arch.default_tsc_khz); + + ret = setup_tdparams_eptp_controls(cpuid, td_params); + if (ret) + return ret; + + ret = setup_tdparams_cpuids(cpuid, td_params); + if (ret) + return ret; + +#define MEMCPY_SAME_SIZE(dst, src) \ + do { \ + BUILD_BUG_ON(sizeof(dst) != sizeof(src)); \ + memcpy((dst), (src), sizeof(dst)); \ + } while (0) + + MEMCPY_SAME_SIZE(td_params->mrconfigid, init_vm->mrconfigid); + MEMCPY_SAME_SIZE(td_params->mrowner, init_vm->mrowner); + MEMCPY_SAME_SIZE(td_params->mrownerconfig, init_vm->mrownerconfig); + + return 0; +} + +static int __tdx_td_init(struct kvm *kvm, struct td_params *td_params, + u64 *seamcall_err) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + cpumask_var_t packages; + struct page **tdcs_pages = NULL; + struct page *tdr_page; + int ret, i; + u64 err, rcx; + + *seamcall_err = 0; + ret = tdx_guest_keyid_alloc(); + if (ret < 0) + return ret; + kvm_tdx->hkid = ret; + kvm_tdx->misc_cg = get_current_misc_cg(); + ret = misc_cg_try_charge(MISC_CG_RES_TDX, kvm_tdx->misc_cg, 1); + if (ret) + goto free_hkid; + + ret = -ENOMEM; + + atomic_inc(&nr_configured_hkid); + + tdr_page = alloc_page(GFP_KERNEL); + if (!tdr_page) + goto free_hkid; + + kvm_tdx->td.tdcs_nr_pages = tdx_sysinfo->td_ctrl.tdcs_base_size / PAGE_SIZE; + /* TDVPS = TDVPR(4K page) + TDCX(multiple 4K pages), -1 for TDVPR. */ + kvm_tdx->td.tdcx_nr_pages = tdx_sysinfo->td_ctrl.tdvps_base_size / PAGE_SIZE - 1; + tdcs_pages = kcalloc(kvm_tdx->td.tdcs_nr_pages, sizeof(*kvm_tdx->td.tdcs_pages), + GFP_KERNEL | __GFP_ZERO); + if (!tdcs_pages) + goto free_tdr; + + for (i = 0; i < kvm_tdx->td.tdcs_nr_pages; i++) { + tdcs_pages[i] = alloc_page(GFP_KERNEL); + if (!tdcs_pages[i]) + goto free_tdcs; + } + + if (!zalloc_cpumask_var(&packages, GFP_KERNEL)) + goto free_tdcs; + + cpus_read_lock(); + + /* + * Need at least one CPU of the package to be online in order to + * program all packages for host key id. Check it. + */ + for_each_present_cpu(i) + cpumask_set_cpu(topology_physical_package_id(i), packages); + for_each_online_cpu(i) + cpumask_clear_cpu(topology_physical_package_id(i), packages); + if (!cpumask_empty(packages)) { + ret = -EIO; + /* + * Because it's hard for human operator to figure out the + * reason, warn it. + */ +#define MSG_ALLPKG "All packages need to have online CPU to create TD. Online CPU and retry.\n" + pr_warn_ratelimited(MSG_ALLPKG); + goto free_packages; + } + + /* + * TDH.MNG.CREATE tries to grab the global TDX module and fails + * with TDX_OPERAND_BUSY when it fails to grab. Take the global + * lock to prevent it from failure. + */ + mutex_lock(&tdx_lock); + kvm_tdx->td.tdr_page = tdr_page; + err = tdh_mng_create(&kvm_tdx->td, kvm_tdx->hkid); + mutex_unlock(&tdx_lock); + + if (err == TDX_RND_NO_ENTROPY) { + ret = -EAGAIN; + goto free_packages; + } + + if (WARN_ON_ONCE(err)) { + pr_tdx_error(TDH_MNG_CREATE, err); + ret = -EIO; + goto free_packages; + } + + for_each_online_cpu(i) { + int pkg = topology_physical_package_id(i); + + if (cpumask_test_and_set_cpu(pkg, packages)) + continue; + + /* + * Program the memory controller in the package with an + * encryption key associated to a TDX private host key id + * assigned to this TDR. Concurrent operations on same memory + * controller results in TDX_OPERAND_BUSY. No locking needed + * beyond the cpus_read_lock() above as it serializes against + * hotplug and the first online CPU of the package is always + * used. We never have two CPUs in the same socket trying to + * program the key. + */ + ret = smp_call_on_cpu(i, tdx_do_tdh_mng_key_config, + kvm_tdx, true); + if (ret) + break; + } + cpus_read_unlock(); + free_cpumask_var(packages); + if (ret) { + i = 0; + goto teardown; + } + + kvm_tdx->td.tdcs_pages = tdcs_pages; + for (i = 0; i < kvm_tdx->td.tdcs_nr_pages; i++) { + err = tdh_mng_addcx(&kvm_tdx->td, tdcs_pages[i]); + if (err == TDX_RND_NO_ENTROPY) { + /* Here it's hard to allow userspace to retry. */ + ret = -EAGAIN; + goto teardown; + } + if (WARN_ON_ONCE(err)) { + pr_tdx_error(TDH_MNG_ADDCX, err); + ret = -EIO; + goto teardown; + } + } + + err = tdh_mng_init(&kvm_tdx->td, __pa(td_params), &rcx); + if ((err & TDX_SEAMCALL_STATUS_MASK) == TDX_OPERAND_INVALID) { + /* + * Because a user gives operands, don't warn. + * Return a hint to the user because it's sometimes hard for the + * user to figure out which operand is invalid. SEAMCALL status + * code includes which operand caused invalid operand error. + */ + *seamcall_err = err; + ret = -EINVAL; + goto teardown; + } else if (WARN_ON_ONCE(err)) { + pr_tdx_error_1(TDH_MNG_INIT, err, rcx); + ret = -EIO; + goto teardown; + } + + return 0; + + /* + * The sequence for freeing resources from a partially initialized TD + * varies based on where in the initialization flow failure occurred. + * Simply use the full teardown and destroy, which naturally play nice + * with partial initialization. + */ +teardown: + /* Only free pages not yet added, so start at 'i' */ + for (; i < kvm_tdx->td.tdcs_nr_pages; i++) { + if (tdcs_pages[i]) { + __free_page(tdcs_pages[i]); + tdcs_pages[i] = NULL; + } + } + if (!kvm_tdx->td.tdcs_pages) + kfree(tdcs_pages); + + tdx_mmu_release_hkid(kvm); + tdx_reclaim_td_control_pages(kvm); + + return ret; + +free_packages: + cpus_read_unlock(); + free_cpumask_var(packages); + +free_tdcs: + for (i = 0; i < kvm_tdx->td.tdcs_nr_pages; i++) { + if (tdcs_pages[i]) + __free_page(tdcs_pages[i]); + } + kfree(tdcs_pages); + kvm_tdx->td.tdcs_pages = NULL; + +free_tdr: + if (tdr_page) + __free_page(tdr_page); + kvm_tdx->td.tdr_page = 0; + +free_hkid: + tdx_hkid_free(kvm_tdx); + + return ret; +} + +static u64 tdx_td_metadata_field_read(struct kvm_tdx *tdx, u64 field_id, + u64 *data) +{ + u64 err; + + err = tdh_mng_rd(&tdx->td, field_id, data); + + return err; +} + +#define TDX_MD_UNREADABLE_LEAF_MASK GENMASK(30, 7) +#define TDX_MD_UNREADABLE_SUBLEAF_MASK GENMASK(31, 7) + +static int tdx_read_cpuid(struct kvm_vcpu *vcpu, u32 leaf, u32 sub_leaf, + bool sub_leaf_set, int *entry_index, + struct kvm_cpuid_entry2 *out) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + u64 field_id = TD_MD_FIELD_ID_CPUID_VALUES; + u64 ebx_eax, edx_ecx; + u64 err = 0; + + if (sub_leaf > 0b1111111) + return -EINVAL; + + if (*entry_index >= KVM_MAX_CPUID_ENTRIES) + return -EINVAL; + + if (leaf & TDX_MD_UNREADABLE_LEAF_MASK || + sub_leaf & TDX_MD_UNREADABLE_SUBLEAF_MASK) + return -EINVAL; + + /* + * bit 23:17, REVSERVED: reserved, must be 0; + * bit 16, LEAF_31: leaf number bit 31; + * bit 15:9, LEAF_6_0: leaf number bits 6:0, leaf bits 30:7 are + * implicitly 0; + * bit 8, SUBLEAF_NA: sub-leaf not applicable flag; + * bit 7:1, SUBLEAF_6_0: sub-leaf number bits 6:0. If SUBLEAF_NA is 1, + * the SUBLEAF_6_0 is all-1. + * sub-leaf bits 31:7 are implicitly 0; + * bit 0, ELEMENT_I: Element index within field; + */ + field_id |= ((leaf & 0x80000000) ? 1 : 0) << 16; + field_id |= (leaf & 0x7f) << 9; + if (sub_leaf_set) + field_id |= (sub_leaf & 0x7f) << 1; + else + field_id |= 0x1fe; + + err = tdx_td_metadata_field_read(kvm_tdx, field_id, &ebx_eax); + if (err) //TODO check for specific errors + goto err_out; + + out->eax = (u32) ebx_eax; + out->ebx = (u32) (ebx_eax >> 32); + + field_id++; + err = tdx_td_metadata_field_read(kvm_tdx, field_id, &edx_ecx); + /* + * It's weird that reading edx_ecx fails while reading ebx_eax + * succeeded. + */ + if (WARN_ON_ONCE(err)) + goto err_out; + + out->ecx = (u32) edx_ecx; + out->edx = (u32) (edx_ecx >> 32); + + out->function = leaf; + out->index = sub_leaf; + out->flags |= sub_leaf_set ? KVM_CPUID_FLAG_SIGNIFCANT_INDEX : 0; + + /* + * Work around missing support on old TDX modules, fetch + * guest maxpa from gfn_direct_bits. + */ + if (leaf == 0x80000008) { + gpa_t gpa_bits = gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm)); + unsigned int g_maxpa = __ffs(gpa_bits) + 1; + + out->eax = tdx_set_guest_phys_addr_bits(out->eax, g_maxpa); + } + + (*entry_index)++; + + return 0; + +err_out: + out->eax = 0; + out->ebx = 0; + out->ecx = 0; + out->edx = 0; + + return -EIO; +} + +static int tdx_td_init(struct kvm *kvm, struct kvm_tdx_cmd *cmd) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + struct kvm_tdx_init_vm *init_vm; + struct td_params *td_params = NULL; + int ret; + + BUILD_BUG_ON(sizeof(*init_vm) != 256 + sizeof_field(struct kvm_tdx_init_vm, cpuid)); + BUILD_BUG_ON(sizeof(struct td_params) != 1024); + + if (kvm_tdx->state != TD_STATE_UNINITIALIZED) + return -EINVAL; + + if (cmd->flags) + return -EINVAL; + + init_vm = kmalloc(sizeof(*init_vm) + + sizeof(init_vm->cpuid.entries[0]) * KVM_MAX_CPUID_ENTRIES, + GFP_KERNEL); + if (!init_vm) + return -ENOMEM; + + if (copy_from_user(init_vm, u64_to_user_ptr(cmd->data), sizeof(*init_vm))) { + ret = -EFAULT; + goto out; + } + + if (init_vm->cpuid.nent > KVM_MAX_CPUID_ENTRIES) { + ret = -E2BIG; + goto out; + } + + if (copy_from_user(init_vm->cpuid.entries, + u64_to_user_ptr(cmd->data) + sizeof(*init_vm), + flex_array_size(init_vm, cpuid.entries, init_vm->cpuid.nent))) { + ret = -EFAULT; + goto out; + } + + if (memchr_inv(init_vm->reserved, 0, sizeof(init_vm->reserved))) { + ret = -EINVAL; + goto out; + } + + if (init_vm->cpuid.padding) { + ret = -EINVAL; + goto out; + } + + td_params = kzalloc(sizeof(struct td_params), GFP_KERNEL); + if (!td_params) { + ret = -ENOMEM; + goto out; + } + + ret = setup_tdparams(kvm, td_params, init_vm); + if (ret) + goto out; + + ret = __tdx_td_init(kvm, td_params, &cmd->hw_error); + if (ret) + goto out; + + kvm_tdx->tsc_offset = td_tdcs_exec_read64(kvm_tdx, TD_TDCS_EXEC_TSC_OFFSET); + kvm_tdx->tsc_multiplier = td_tdcs_exec_read64(kvm_tdx, TD_TDCS_EXEC_TSC_MULTIPLIER); + kvm_tdx->attributes = td_params->attributes; + kvm_tdx->xfam = td_params->xfam; + + if (td_params->config_flags & TDX_CONFIG_FLAGS_MAX_GPAW) + kvm->arch.gfn_direct_bits = TDX_SHARED_BIT_PWL_5; + else + kvm->arch.gfn_direct_bits = TDX_SHARED_BIT_PWL_4; + + kvm_tdx->state = TD_STATE_INITIALIZED; +out: + /* kfree() accepts NULL. */ + kfree(init_vm); + kfree(td_params); + + return ret; +} + +void tdx_flush_tlb_current(struct kvm_vcpu *vcpu) +{ + /* + * flush_tlb_current() is invoked when the first time for the vcpu to + * run or when root of shared EPT is invalidated. + * KVM only needs to flush shared EPT because the TDX module handles TLB + * invalidation for private EPT in tdh_vp_enter(); + * + * A single context invalidation for shared EPT can be performed here. + * However, this single context invalidation requires the private EPTP + * rather than the shared EPTP to flush shared EPT, as shared EPT uses + * private EPTP as its ASID for TLB invalidation. + * + * To avoid reading back private EPTP, perform a global invalidation for + * shared EPT instead to keep this function simple. + */ + ept_sync_global(); +} + +void tdx_flush_tlb_all(struct kvm_vcpu *vcpu) +{ + /* + * TDX has called tdx_track() in tdx_sept_remove_private_spte() to + * ensure that private EPT will be flushed on the next TD enter. No need + * to call tdx_track() here again even when this callback is a result of + * zapping private EPT. + * + * Due to the lack of the context to determine which EPT has been + * affected by zapping, invoke invept() directly here for both shared + * EPT and private EPT for simplicity, though it's not necessary for + * private EPT. + */ + ept_sync_global(); +} + +static int tdx_td_finalize(struct kvm *kvm, struct kvm_tdx_cmd *cmd) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + + guard(mutex)(&kvm->slots_lock); + + if (!is_hkid_assigned(kvm_tdx) || kvm_tdx->state == TD_STATE_RUNNABLE) + return -EINVAL; + /* + * Pages are pending for KVM_TDX_INIT_MEM_REGION to issue + * TDH.MEM.PAGE.ADD(). + */ + if (atomic64_read(&kvm_tdx->nr_premapped)) + return -EINVAL; + + cmd->hw_error = tdh_mr_finalize(&kvm_tdx->td); + if (tdx_operand_busy(cmd->hw_error)) + return -EBUSY; + if (KVM_BUG_ON(cmd->hw_error, kvm)) { + pr_tdx_error(TDH_MR_FINALIZE, cmd->hw_error); + return -EIO; + } + + kvm_tdx->state = TD_STATE_RUNNABLE; + /* TD_STATE_RUNNABLE must be set before 'pre_fault_allowed' */ + smp_wmb(); + kvm->arch.pre_fault_allowed = true; + return 0; +} + +int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) +{ + struct kvm_tdx_cmd tdx_cmd; + int r; + + if (copy_from_user(&tdx_cmd, argp, sizeof(struct kvm_tdx_cmd))) + return -EFAULT; + + /* + * Userspace should never set hw_error. It is used to fill + * hardware-defined error by the kernel. + */ + if (tdx_cmd.hw_error) + return -EINVAL; + + mutex_lock(&kvm->lock); + + switch (tdx_cmd.id) { + case KVM_TDX_CAPABILITIES: + r = tdx_get_capabilities(&tdx_cmd); + break; + case KVM_TDX_INIT_VM: + r = tdx_td_init(kvm, &tdx_cmd); + break; + case KVM_TDX_FINALIZE_VM: + r = tdx_td_finalize(kvm, &tdx_cmd); + break; + default: + r = -EINVAL; + goto out; + } + + if (copy_to_user(argp, &tdx_cmd, sizeof(struct kvm_tdx_cmd))) + r = -EFAULT; + +out: + mutex_unlock(&kvm->lock); + return r; +} + +/* VMM can pass one 64bit auxiliary data to vcpu via RCX for guest BIOS. */ +static int tdx_td_vcpu_init(struct kvm_vcpu *vcpu, u64 vcpu_rcx) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + struct vcpu_tdx *tdx = to_tdx(vcpu); + struct page *page; + int ret, i; + u64 err; + + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + tdx->vp.tdvpr_page = page; + + tdx->vp.tdcx_pages = kcalloc(kvm_tdx->td.tdcx_nr_pages, sizeof(*tdx->vp.tdcx_pages), + GFP_KERNEL); + if (!tdx->vp.tdcx_pages) { + ret = -ENOMEM; + goto free_tdvpr; + } + + for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) { + page = alloc_page(GFP_KERNEL); + if (!page) { + ret = -ENOMEM; + goto free_tdcx; + } + tdx->vp.tdcx_pages[i] = page; + } + + err = tdh_vp_create(&kvm_tdx->td, &tdx->vp); + if (KVM_BUG_ON(err, vcpu->kvm)) { + ret = -EIO; + pr_tdx_error(TDH_VP_CREATE, err); + goto free_tdcx; + } + + for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) { + err = tdh_vp_addcx(&tdx->vp, tdx->vp.tdcx_pages[i]); + if (KVM_BUG_ON(err, vcpu->kvm)) { + pr_tdx_error(TDH_VP_ADDCX, err); + /* + * Pages already added are reclaimed by the vcpu_free + * method, but the rest are freed here. + */ + for (; i < kvm_tdx->td.tdcx_nr_pages; i++) { + __free_page(tdx->vp.tdcx_pages[i]); + tdx->vp.tdcx_pages[i] = NULL; + } + return -EIO; + } + } + + err = tdh_vp_init(&tdx->vp, vcpu_rcx, vcpu->vcpu_id); + if (KVM_BUG_ON(err, vcpu->kvm)) { + pr_tdx_error(TDH_VP_INIT, err); + return -EIO; + } + + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + + return 0; + +free_tdcx: + for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) { + if (tdx->vp.tdcx_pages[i]) + __free_page(tdx->vp.tdcx_pages[i]); + tdx->vp.tdcx_pages[i] = NULL; + } + kfree(tdx->vp.tdcx_pages); + tdx->vp.tdcx_pages = NULL; + +free_tdvpr: + if (tdx->vp.tdvpr_page) + __free_page(tdx->vp.tdvpr_page); + tdx->vp.tdvpr_page = 0; + + return ret; +} + +/* Sometimes reads multipple subleafs. Return how many enties were written. */ +static int tdx_vcpu_get_cpuid_leaf(struct kvm_vcpu *vcpu, u32 leaf, int *entry_index, + struct kvm_cpuid_entry2 *output_e) +{ + int sub_leaf = 0; + int ret; + + /* First try without a subleaf */ + ret = tdx_read_cpuid(vcpu, leaf, 0, false, entry_index, output_e); + + /* If success, or invalid leaf, just give up */ + if (ret != -EIO) + return ret; + + /* + * If the try without a subleaf failed, try reading subleafs until + * failure. The TDX module only supports 6 bits of subleaf index. + */ + while (1) { + /* Keep reading subleafs until there is a failure. */ + if (tdx_read_cpuid(vcpu, leaf, sub_leaf, true, entry_index, output_e)) + return !sub_leaf; + + sub_leaf++; + output_e++; + } + + return 0; +} + +static int tdx_vcpu_get_cpuid(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd) +{ + struct kvm_cpuid2 __user *output, *td_cpuid; + int r = 0, i = 0, leaf; + u32 level; + + output = u64_to_user_ptr(cmd->data); + td_cpuid = kzalloc(sizeof(*td_cpuid) + + sizeof(output->entries[0]) * KVM_MAX_CPUID_ENTRIES, + GFP_KERNEL); + if (!td_cpuid) + return -ENOMEM; + + if (copy_from_user(td_cpuid, output, sizeof(*output))) { + r = -EFAULT; + goto out; + } + + /* Read max CPUID for normal range */ + if (tdx_vcpu_get_cpuid_leaf(vcpu, 0, &i, &td_cpuid->entries[i])) { + r = -EIO; + goto out; + } + level = td_cpuid->entries[0].eax; + + for (leaf = 1; leaf <= level; leaf++) + tdx_vcpu_get_cpuid_leaf(vcpu, leaf, &i, &td_cpuid->entries[i]); + + /* Read max CPUID for extended range */ + if (tdx_vcpu_get_cpuid_leaf(vcpu, 0x80000000, &i, &td_cpuid->entries[i])) { + r = -EIO; + goto out; + } + level = td_cpuid->entries[i - 1].eax; + + for (leaf = 0x80000001; leaf <= level; leaf++) + tdx_vcpu_get_cpuid_leaf(vcpu, leaf, &i, &td_cpuid->entries[i]); + + if (td_cpuid->nent < i) + r = -E2BIG; + td_cpuid->nent = i; + + if (copy_to_user(output, td_cpuid, sizeof(*output))) { + r = -EFAULT; + goto out; + } + + if (r == -E2BIG) + goto out; + + if (copy_to_user(output->entries, td_cpuid->entries, + td_cpuid->nent * sizeof(struct kvm_cpuid_entry2))) + r = -EFAULT; + +out: + kfree(td_cpuid); + + return r; +} + +static int tdx_vcpu_init(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd) +{ + u64 apic_base; + struct vcpu_tdx *tdx = to_tdx(vcpu); + int ret; + + if (cmd->flags) + return -EINVAL; + + if (tdx->state != VCPU_TD_STATE_UNINITIALIZED) + return -EINVAL; + + /* + * TDX requires X2APIC, userspace is responsible for configuring guest + * CPUID accordingly. + */ + apic_base = APIC_DEFAULT_PHYS_BASE | LAPIC_MODE_X2APIC | + (kvm_vcpu_is_reset_bsp(vcpu) ? MSR_IA32_APICBASE_BSP : 0); + if (kvm_apic_set_base(vcpu, apic_base, true)) + return -EINVAL; + + ret = tdx_td_vcpu_init(vcpu, (u64)cmd->data); + if (ret) + return ret; + + td_vmcs_write16(tdx, POSTED_INTR_NV, POSTED_INTR_VECTOR); + td_vmcs_write64(tdx, POSTED_INTR_DESC_ADDR, __pa(&tdx->vt.pi_desc)); + td_vmcs_setbit32(tdx, PIN_BASED_VM_EXEC_CONTROL, PIN_BASED_POSTED_INTR); + + tdx->state = VCPU_TD_STATE_INITIALIZED; + + return 0; +} + +void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) +{ + /* + * Yell on INIT, as TDX doesn't support INIT, i.e. KVM should drop all + * INIT events. + * + * Defer initializing vCPU for RESET state until KVM_TDX_INIT_VCPU, as + * userspace needs to define the vCPU model before KVM can initialize + * vCPU state, e.g. to enable x2APIC. + */ + WARN_ON_ONCE(init_event); +} + +struct tdx_gmem_post_populate_arg { + struct kvm_vcpu *vcpu; + __u32 flags; +}; + +static int tdx_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, + void __user *src, int order, void *_arg) +{ + u64 error_code = PFERR_GUEST_FINAL_MASK | PFERR_PRIVATE_ACCESS; + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + struct tdx_gmem_post_populate_arg *arg = _arg; + struct kvm_vcpu *vcpu = arg->vcpu; + gpa_t gpa = gfn_to_gpa(gfn); + u8 level = PG_LEVEL_4K; + struct page *src_page; + int ret, i; + u64 err, entry, level_state; + + /* + * Get the source page if it has been faulted in. Return failure if the + * source page has been swapped out or unmapped in primary memory. + */ + ret = get_user_pages_fast((unsigned long)src, 1, 0, &src_page); + if (ret < 0) + return ret; + if (ret != 1) + return -ENOMEM; + + ret = kvm_tdp_map_page(vcpu, gpa, error_code, &level); + if (ret < 0) + goto out; + + /* + * The private mem cannot be zapped after kvm_tdp_map_page() + * because all paths are covered by slots_lock and the + * filemap invalidate lock. Check that they are indeed enough. + */ + if (IS_ENABLED(CONFIG_KVM_PROVE_MMU)) { + scoped_guard(read_lock, &kvm->mmu_lock) { + if (KVM_BUG_ON(!kvm_tdp_mmu_gpa_is_mapped(vcpu, gpa), kvm)) { + ret = -EIO; + goto out; + } + } + } + + ret = 0; + err = tdh_mem_page_add(&kvm_tdx->td, gpa, pfn_to_page(pfn), + src_page, &entry, &level_state); + if (err) { + ret = unlikely(tdx_operand_busy(err)) ? -EBUSY : -EIO; + goto out; + } + + if (!KVM_BUG_ON(!atomic64_read(&kvm_tdx->nr_premapped), kvm)) + atomic64_dec(&kvm_tdx->nr_premapped); + + if (arg->flags & KVM_TDX_MEASURE_MEMORY_REGION) { + for (i = 0; i < PAGE_SIZE; i += TDX_EXTENDMR_CHUNKSIZE) { + err = tdh_mr_extend(&kvm_tdx->td, gpa + i, &entry, + &level_state); + if (err) { + ret = -EIO; + break; + } + } + } + +out: + put_page(src_page); + return ret; +} + +static int tdx_vcpu_init_mem_region(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + struct kvm *kvm = vcpu->kvm; + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + struct kvm_tdx_init_mem_region region; + struct tdx_gmem_post_populate_arg arg; + long gmem_ret; + int ret; + + if (tdx->state != VCPU_TD_STATE_INITIALIZED) + return -EINVAL; + + guard(mutex)(&kvm->slots_lock); + + /* Once TD is finalized, the initial guest memory is fixed. */ + if (kvm_tdx->state == TD_STATE_RUNNABLE) + return -EINVAL; + + if (cmd->flags & ~KVM_TDX_MEASURE_MEMORY_REGION) + return -EINVAL; + + if (copy_from_user(®ion, u64_to_user_ptr(cmd->data), sizeof(region))) + return -EFAULT; + + if (!PAGE_ALIGNED(region.source_addr) || !PAGE_ALIGNED(region.gpa) || + !region.nr_pages || + region.gpa + (region.nr_pages << PAGE_SHIFT) <= region.gpa || + !vt_is_tdx_private_gpa(kvm, region.gpa) || + !vt_is_tdx_private_gpa(kvm, region.gpa + (region.nr_pages << PAGE_SHIFT) - 1)) + return -EINVAL; + + kvm_mmu_reload(vcpu); + ret = 0; + while (region.nr_pages) { + if (signal_pending(current)) { + ret = -EINTR; + break; + } + + arg = (struct tdx_gmem_post_populate_arg) { + .vcpu = vcpu, + .flags = cmd->flags, + }; + gmem_ret = kvm_gmem_populate(kvm, gpa_to_gfn(region.gpa), + u64_to_user_ptr(region.source_addr), + 1, tdx_gmem_post_populate, &arg); + if (gmem_ret < 0) { + ret = gmem_ret; + break; + } + + if (gmem_ret != 1) { + ret = -EIO; + break; + } + + region.source_addr += PAGE_SIZE; + region.gpa += PAGE_SIZE; + region.nr_pages--; + + cond_resched(); + } + + if (copy_to_user(u64_to_user_ptr(cmd->data), ®ion, sizeof(region))) + ret = -EFAULT; + return ret; +} + +int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + struct kvm_tdx_cmd cmd; + int ret; + + if (!is_hkid_assigned(kvm_tdx) || kvm_tdx->state == TD_STATE_RUNNABLE) + return -EINVAL; + + if (copy_from_user(&cmd, argp, sizeof(cmd))) + return -EFAULT; + + if (cmd.hw_error) + return -EINVAL; + + switch (cmd.id) { + case KVM_TDX_INIT_VCPU: + ret = tdx_vcpu_init(vcpu, &cmd); + break; + case KVM_TDX_INIT_MEM_REGION: + ret = tdx_vcpu_init_mem_region(vcpu, &cmd); + break; + case KVM_TDX_GET_CPUID: + ret = tdx_vcpu_get_cpuid(vcpu, &cmd); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) +{ + return PG_LEVEL_4K; +} + +static int tdx_online_cpu(unsigned int cpu) +{ + unsigned long flags; + int r; + + /* Sanity check CPU is already in post-VMXON */ + WARN_ON_ONCE(!(cr4_read_shadow() & X86_CR4_VMXE)); + + local_irq_save(flags); + r = tdx_cpu_enable(); + local_irq_restore(flags); + + return r; +} + +static int tdx_offline_cpu(unsigned int cpu) +{ + int i; + + /* No TD is running. Allow any cpu to be offline. */ + if (!atomic_read(&nr_configured_hkid)) + return 0; + + /* + * In order to reclaim TDX HKID, (i.e. when deleting guest TD), need to + * call TDH.PHYMEM.PAGE.WBINVD on all packages to program all memory + * controller with pconfig. If we have active TDX HKID, refuse to + * offline the last online cpu. + */ + for_each_online_cpu(i) { + /* + * Found another online cpu on the same package. + * Allow to offline. + */ + if (i != cpu && topology_physical_package_id(i) == + topology_physical_package_id(cpu)) + return 0; + } + + /* + * This is the last cpu of this package. Don't offline it. + * + * Because it's hard for human operator to understand the + * reason, warn it. + */ +#define MSG_ALLPKG_ONLINE \ + "TDX requires all packages to have an online CPU. Delete all TDs in order to offline all CPUs of a package.\n" + pr_warn_ratelimited(MSG_ALLPKG_ONLINE); + return -EBUSY; +} + +static void __do_tdx_cleanup(void) +{ + /* + * Once TDX module is initialized, it cannot be disabled and + * re-initialized again w/o runtime update (which isn't + * supported by kernel). Only need to remove the cpuhp here. + * The TDX host core code tracks TDX status and can handle + * 'multiple enabling' scenario. + */ + WARN_ON_ONCE(!tdx_cpuhp_state); + cpuhp_remove_state_nocalls_cpuslocked(tdx_cpuhp_state); + tdx_cpuhp_state = 0; +} + +static void __tdx_cleanup(void) +{ + cpus_read_lock(); + __do_tdx_cleanup(); + cpus_read_unlock(); +} + +static int __init __do_tdx_bringup(void) +{ + int r; + + /* + * TDX-specific cpuhp callback to call tdx_cpu_enable() on all + * online CPUs before calling tdx_enable(), and on any new + * going-online CPU to make sure it is ready for TDX guest. + */ + r = cpuhp_setup_state_cpuslocked(CPUHP_AP_ONLINE_DYN, + "kvm/cpu/tdx:online", + tdx_online_cpu, tdx_offline_cpu); + if (r < 0) + return r; + + tdx_cpuhp_state = r; + + r = tdx_enable(); + if (r) + __do_tdx_cleanup(); + + return r; +} + +static int __init __tdx_bringup(void) +{ + const struct tdx_sys_info_td_conf *td_conf; + int r, i; + + for (i = 0; i < ARRAY_SIZE(tdx_uret_msrs); i++) { + /* + * Check if MSRs (tdx_uret_msrs) can be saved/restored + * before returning to user space. + * + * this_cpu_ptr(user_return_msrs)->registered isn't checked + * because the registration is done at vcpu runtime by + * tdx_user_return_msr_update_cache(). + */ + tdx_uret_msrs[i].slot = kvm_find_user_return_msr(tdx_uret_msrs[i].msr); + if (tdx_uret_msrs[i].slot == -1) { + /* If any MSR isn't supported, it is a KVM bug */ + pr_err("MSR %x isn't included by kvm_find_user_return_msr\n", + tdx_uret_msrs[i].msr); + return -EIO; + } + } + + /* + * Enabling TDX requires enabling hardware virtualization first, + * as making SEAMCALLs requires CPU being in post-VMXON state. + */ + r = kvm_enable_virtualization(); + if (r) + return r; + + cpus_read_lock(); + r = __do_tdx_bringup(); + cpus_read_unlock(); + + if (r) + goto tdx_bringup_err; + + /* Get TDX global information for later use */ + tdx_sysinfo = tdx_get_sysinfo(); + if (WARN_ON_ONCE(!tdx_sysinfo)) { + r = -EINVAL; + goto get_sysinfo_err; + } + + /* Check TDX module and KVM capabilities */ + if (!tdx_get_supported_attrs(&tdx_sysinfo->td_conf) || + !tdx_get_supported_xfam(&tdx_sysinfo->td_conf)) + goto get_sysinfo_err; + + if (!(tdx_sysinfo->features.tdx_features0 & MD_FIELD_ID_FEATURES0_TOPOLOGY_ENUM)) + goto get_sysinfo_err; + + /* + * TDX has its own limit of maximum vCPUs it can support for all + * TDX guests in addition to KVM_MAX_VCPUS. Userspace needs to + * query TDX guest's maximum vCPUs by checking KVM_CAP_MAX_VCPU + * extension on per-VM basis. + * + * TDX module reports such limit via the MAX_VCPU_PER_TD global + * metadata. Different modules may report different values. + * Some old module may also not support this metadata (in which + * case this limit is U16_MAX). + * + * In practice, the reported value reflects the maximum logical + * CPUs that ALL the platforms that the module supports can + * possibly have. + * + * Simply forwarding the MAX_VCPU_PER_TD to userspace could + * result in an unpredictable ABI. KVM instead always advertise + * the number of logical CPUs the platform has as the maximum + * vCPUs for TDX guests. + * + * Make sure MAX_VCPU_PER_TD reported by TDX module is not + * smaller than the number of logical CPUs, otherwise KVM will + * report an unsupported value to userspace. + * + * Note, a platform with TDX enabled in the BIOS cannot support + * physical CPU hotplug, and TDX requires the BIOS has marked + * all logical CPUs in MADT table as enabled. Just use + * num_present_cpus() for the number of logical CPUs. + */ + td_conf = &tdx_sysinfo->td_conf; + if (td_conf->max_vcpus_per_td < num_present_cpus()) { + pr_err("Disable TDX: MAX_VCPU_PER_TD (%u) smaller than number of logical CPUs (%u).\n", + td_conf->max_vcpus_per_td, num_present_cpus()); + r = -EINVAL; + goto get_sysinfo_err; + } + + if (misc_cg_set_capacity(MISC_CG_RES_TDX, tdx_get_nr_guest_keyids())) { + r = -EINVAL; + goto get_sysinfo_err; + } + + /* + * Leave hardware virtualization enabled after TDX is enabled + * successfully. TDX CPU hotplug depends on this. + */ + return 0; + +get_sysinfo_err: + __tdx_cleanup(); +tdx_bringup_err: + kvm_disable_virtualization(); + return r; +} + +void tdx_cleanup(void) +{ + if (enable_tdx) { + misc_cg_set_capacity(MISC_CG_RES_TDX, 0); + __tdx_cleanup(); + kvm_disable_virtualization(); + } +} + +int __init tdx_bringup(void) +{ + int r, i; + + /* tdx_disable_virtualization_cpu() uses associated_tdvcpus. */ + for_each_possible_cpu(i) + INIT_LIST_HEAD(&per_cpu(associated_tdvcpus, i)); + + if (!enable_tdx) + return 0; + + if (!enable_ept) { + pr_err("EPT is required for TDX\n"); + goto success_disable_tdx; + } + + if (!tdp_mmu_enabled || !enable_mmio_caching || !enable_ept_ad_bits) { + pr_err("TDP MMU and MMIO caching and EPT A/D bit is required for TDX\n"); + goto success_disable_tdx; + } + + if (!enable_apicv) { + pr_err("APICv is required for TDX\n"); + goto success_disable_tdx; + } + + if (!cpu_feature_enabled(X86_FEATURE_OSXSAVE)) { + pr_err("tdx: OSXSAVE is required for TDX\n"); + goto success_disable_tdx; + } + + if (!cpu_feature_enabled(X86_FEATURE_MOVDIR64B)) { + pr_err("tdx: MOVDIR64B is required for TDX\n"); + goto success_disable_tdx; + } + + if (!cpu_feature_enabled(X86_FEATURE_SELFSNOOP)) { + pr_err("Self-snoop is required for TDX\n"); + goto success_disable_tdx; + } + + if (!cpu_feature_enabled(X86_FEATURE_TDX_HOST_PLATFORM)) { + pr_err("tdx: no TDX private KeyIDs available\n"); + goto success_disable_tdx; + } + + if (!enable_virt_at_load) { + pr_err("tdx: tdx requires kvm.enable_virt_at_load=1\n"); + goto success_disable_tdx; + } + + /* + * Ideally KVM should probe whether TDX module has been loaded + * first and then try to bring it up. But TDX needs to use SEAMCALL + * to probe whether the module is loaded (there is no CPUID or MSR + * for that), and making SEAMCALL requires enabling virtualization + * first, just like the rest steps of bringing up TDX module. + * + * So, for simplicity do everything in __tdx_bringup(); the first + * SEAMCALL will return -ENODEV when the module is not loaded. The + * only complication is having to make sure that initialization + * SEAMCALLs don't return TDX_SEAMCALL_VMFAILINVALID in other + * cases. + */ + r = __tdx_bringup(); + if (r) { + /* + * Disable TDX only but don't fail to load module if + * the TDX module could not be loaded. No need to print + * message saying "module is not loaded" because it was + * printed when the first SEAMCALL failed. + */ + if (r == -ENODEV) + goto success_disable_tdx; + + enable_tdx = 0; + } + + return r; + +success_disable_tdx: + enable_tdx = 0; + return 0; +} diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h new file mode 100644 index 000000000000..51f98443e8a2 --- /dev/null +++ b/arch/x86/kvm/vmx/tdx.h @@ -0,0 +1,204 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_VMX_TDX_H +#define __KVM_X86_VMX_TDX_H + +#include "tdx_arch.h" +#include "tdx_errno.h" + +#ifdef CONFIG_KVM_INTEL_TDX +#include "common.h" + +int tdx_bringup(void); +void tdx_cleanup(void); + +extern bool enable_tdx; + +/* TDX module hardware states. These follow the TDX module OP_STATEs. */ +enum kvm_tdx_state { + TD_STATE_UNINITIALIZED = 0, + TD_STATE_INITIALIZED, + TD_STATE_RUNNABLE, +}; + +struct kvm_tdx { + struct kvm kvm; + + struct misc_cg *misc_cg; + int hkid; + enum kvm_tdx_state state; + + u64 attributes; + u64 xfam; + + u64 tsc_offset; + u64 tsc_multiplier; + + struct tdx_td td; + + /* For KVM_TDX_INIT_MEM_REGION. */ + atomic64_t nr_premapped; + + /* + * Prevent vCPUs from TD entry to ensure SEPT zap related SEAMCALLs do + * not contend with tdh_vp_enter() and TDCALLs. + * Set/unset is protected with kvm->mmu_lock. + */ + bool wait_for_sept_zap; +}; + +/* TDX module vCPU states */ +enum vcpu_tdx_state { + VCPU_TD_STATE_UNINITIALIZED = 0, + VCPU_TD_STATE_INITIALIZED, +}; + +struct vcpu_tdx { + struct kvm_vcpu vcpu; + struct vcpu_vt vt; + u64 ext_exit_qualification; + gpa_t exit_gpa; + struct tdx_module_args vp_enter_args; + + struct tdx_vp vp; + + struct list_head cpu_list; + + u64 vp_enter_ret; + + enum vcpu_tdx_state state; + bool guest_entered; + + u64 map_gpa_next; + u64 map_gpa_end; +}; + +void tdh_vp_rd_failed(struct vcpu_tdx *tdx, char *uclass, u32 field, u64 err); +void tdh_vp_wr_failed(struct vcpu_tdx *tdx, char *uclass, char *op, u32 field, + u64 val, u64 err); + +static __always_inline u64 td_tdcs_exec_read64(struct kvm_tdx *kvm_tdx, u32 field) +{ + u64 err, data; + + err = tdh_mng_rd(&kvm_tdx->td, TDCS_EXEC(field), &data); + if (unlikely(err)) { + pr_err("TDH_MNG_RD[EXEC.0x%x] failed: 0x%llx\n", field, err); + return 0; + } + return data; +} + +static __always_inline void tdvps_vmcs_check(u32 field, u8 bits) +{ +#define VMCS_ENC_ACCESS_TYPE_MASK 0x1UL +#define VMCS_ENC_ACCESS_TYPE_FULL 0x0UL +#define VMCS_ENC_ACCESS_TYPE_HIGH 0x1UL +#define VMCS_ENC_ACCESS_TYPE(field) ((field) & VMCS_ENC_ACCESS_TYPE_MASK) + + /* TDX is 64bit only. HIGH field isn't supported. */ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && + VMCS_ENC_ACCESS_TYPE(field) == VMCS_ENC_ACCESS_TYPE_HIGH, + "Read/Write to TD VMCS *_HIGH fields not supported"); + + BUILD_BUG_ON(bits != 16 && bits != 32 && bits != 64); + +#define VMCS_ENC_WIDTH_MASK GENMASK(14, 13) +#define VMCS_ENC_WIDTH_16BIT (0UL << 13) +#define VMCS_ENC_WIDTH_64BIT (1UL << 13) +#define VMCS_ENC_WIDTH_32BIT (2UL << 13) +#define VMCS_ENC_WIDTH_NATURAL (3UL << 13) +#define VMCS_ENC_WIDTH(field) ((field) & VMCS_ENC_WIDTH_MASK) + + /* TDX is 64bit only. i.e. natural width = 64bit. */ + BUILD_BUG_ON_MSG(bits != 64 && __builtin_constant_p(field) && + (VMCS_ENC_WIDTH(field) == VMCS_ENC_WIDTH_64BIT || + VMCS_ENC_WIDTH(field) == VMCS_ENC_WIDTH_NATURAL), + "Invalid TD VMCS access for 64-bit field"); + BUILD_BUG_ON_MSG(bits != 32 && __builtin_constant_p(field) && + VMCS_ENC_WIDTH(field) == VMCS_ENC_WIDTH_32BIT, + "Invalid TD VMCS access for 32-bit field"); + BUILD_BUG_ON_MSG(bits != 16 && __builtin_constant_p(field) && + VMCS_ENC_WIDTH(field) == VMCS_ENC_WIDTH_16BIT, + "Invalid TD VMCS access for 16-bit field"); +} + +static __always_inline void tdvps_management_check(u64 field, u8 bits) {} +static __always_inline void tdvps_state_non_arch_check(u64 field, u8 bits) {} + +#define TDX_BUILD_TDVPS_ACCESSORS(bits, uclass, lclass) \ +static __always_inline u##bits td_##lclass##_read##bits(struct vcpu_tdx *tdx, \ + u32 field) \ +{ \ + u64 err, data; \ + \ + tdvps_##lclass##_check(field, bits); \ + err = tdh_vp_rd(&tdx->vp, TDVPS_##uclass(field), &data); \ + if (unlikely(err)) { \ + tdh_vp_rd_failed(tdx, #uclass, field, err); \ + return 0; \ + } \ + return (u##bits)data; \ +} \ +static __always_inline void td_##lclass##_write##bits(struct vcpu_tdx *tdx, \ + u32 field, u##bits val) \ +{ \ + u64 err; \ + \ + tdvps_##lclass##_check(field, bits); \ + err = tdh_vp_wr(&tdx->vp, TDVPS_##uclass(field), val, \ + GENMASK_ULL(bits - 1, 0)); \ + if (unlikely(err)) \ + tdh_vp_wr_failed(tdx, #uclass, " = ", field, (u64)val, err); \ +} \ +static __always_inline void td_##lclass##_setbit##bits(struct vcpu_tdx *tdx, \ + u32 field, u64 bit) \ +{ \ + u64 err; \ + \ + tdvps_##lclass##_check(field, bits); \ + err = tdh_vp_wr(&tdx->vp, TDVPS_##uclass(field), bit, bit); \ + if (unlikely(err)) \ + tdh_vp_wr_failed(tdx, #uclass, " |= ", field, bit, err); \ +} \ +static __always_inline void td_##lclass##_clearbit##bits(struct vcpu_tdx *tdx, \ + u32 field, u64 bit) \ +{ \ + u64 err; \ + \ + tdvps_##lclass##_check(field, bits); \ + err = tdh_vp_wr(&tdx->vp, TDVPS_##uclass(field), 0, bit); \ + if (unlikely(err)) \ + tdh_vp_wr_failed(tdx, #uclass, " &= ~", field, bit, err);\ +} + + +bool tdx_interrupt_allowed(struct kvm_vcpu *vcpu); +int tdx_complete_emulated_msr(struct kvm_vcpu *vcpu, int err); + +TDX_BUILD_TDVPS_ACCESSORS(16, VMCS, vmcs); +TDX_BUILD_TDVPS_ACCESSORS(32, VMCS, vmcs); +TDX_BUILD_TDVPS_ACCESSORS(64, VMCS, vmcs); + +TDX_BUILD_TDVPS_ACCESSORS(8, MANAGEMENT, management); +TDX_BUILD_TDVPS_ACCESSORS(64, STATE_NON_ARCH, state_non_arch); + +#else +static inline int tdx_bringup(void) { return 0; } +static inline void tdx_cleanup(void) {} + +#define enable_tdx 0 + +struct kvm_tdx { + struct kvm kvm; +}; + +struct vcpu_tdx { + struct kvm_vcpu vcpu; +}; + +static inline bool tdx_interrupt_allowed(struct kvm_vcpu *vcpu) { return false; } +static inline int tdx_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) { return 0; } + +#endif + +#endif diff --git a/arch/x86/kvm/vmx/tdx_arch.h b/arch/x86/kvm/vmx/tdx_arch.h new file mode 100644 index 000000000000..a30e880849e3 --- /dev/null +++ b/arch/x86/kvm/vmx/tdx_arch.h @@ -0,0 +1,167 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* architectural constants/data definitions for TDX SEAMCALLs */ + +#ifndef __KVM_X86_TDX_ARCH_H +#define __KVM_X86_TDX_ARCH_H + +#include <linux/types.h> + +/* TDX control structure (TDR/TDCS/TDVPS) field access codes */ +#define TDX_NON_ARCH BIT_ULL(63) +#define TDX_CLASS_SHIFT 56 +#define TDX_FIELD_MASK GENMASK_ULL(31, 0) + +#define __BUILD_TDX_FIELD(non_arch, class, field) \ + (((non_arch) ? TDX_NON_ARCH : 0) | \ + ((u64)(class) << TDX_CLASS_SHIFT) | \ + ((u64)(field) & TDX_FIELD_MASK)) + +#define BUILD_TDX_FIELD(class, field) \ + __BUILD_TDX_FIELD(false, (class), (field)) + +#define BUILD_TDX_FIELD_NON_ARCH(class, field) \ + __BUILD_TDX_FIELD(true, (class), (field)) + + +/* Class code for TD */ +#define TD_CLASS_EXECUTION_CONTROLS 17ULL + +/* Class code for TDVPS */ +#define TDVPS_CLASS_VMCS 0ULL +#define TDVPS_CLASS_GUEST_GPR 16ULL +#define TDVPS_CLASS_OTHER_GUEST 17ULL +#define TDVPS_CLASS_MANAGEMENT 32ULL + +enum tdx_tdcs_execution_control { + TD_TDCS_EXEC_TSC_OFFSET = 10, + TD_TDCS_EXEC_TSC_MULTIPLIER = 11, +}; + +enum tdx_vcpu_guest_other_state { + TD_VCPU_STATE_DETAILS_NON_ARCH = 0x100, +}; + +#define TDX_VCPU_STATE_DETAILS_INTR_PENDING BIT_ULL(0) + +static inline bool tdx_vcpu_state_details_intr_pending(u64 vcpu_state_details) +{ + return !!(vcpu_state_details & TDX_VCPU_STATE_DETAILS_INTR_PENDING); +} + +/* @field is any of enum tdx_tdcs_execution_control */ +#define TDCS_EXEC(field) BUILD_TDX_FIELD(TD_CLASS_EXECUTION_CONTROLS, (field)) + +/* @field is the VMCS field encoding */ +#define TDVPS_VMCS(field) BUILD_TDX_FIELD(TDVPS_CLASS_VMCS, (field)) + +/* @field is any of enum tdx_guest_other_state */ +#define TDVPS_STATE(field) BUILD_TDX_FIELD(TDVPS_CLASS_OTHER_GUEST, (field)) +#define TDVPS_STATE_NON_ARCH(field) BUILD_TDX_FIELD_NON_ARCH(TDVPS_CLASS_OTHER_GUEST, (field)) + +/* Management class fields */ +enum tdx_vcpu_guest_management { + TD_VCPU_PEND_NMI = 11, +}; + +/* @field is any of enum tdx_vcpu_guest_management */ +#define TDVPS_MANAGEMENT(field) BUILD_TDX_FIELD(TDVPS_CLASS_MANAGEMENT, (field)) + +#define TDX_EXTENDMR_CHUNKSIZE 256 + +struct tdx_cpuid_value { + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; +} __packed; + +#define TDX_TD_ATTR_DEBUG BIT_ULL(0) +#define TDX_TD_ATTR_SEPT_VE_DISABLE BIT_ULL(28) +#define TDX_TD_ATTR_PKS BIT_ULL(30) +#define TDX_TD_ATTR_KL BIT_ULL(31) +#define TDX_TD_ATTR_PERFMON BIT_ULL(63) + +#define TDX_EXT_EXIT_QUAL_TYPE_MASK GENMASK(3, 0) +#define TDX_EXT_EXIT_QUAL_TYPE_PENDING_EPT_VIOLATION 6 +/* + * TD_PARAMS is provided as an input to TDH_MNG_INIT, the size of which is 1024B. + */ +struct td_params { + u64 attributes; + u64 xfam; + u16 max_vcpus; + u8 reserved0[6]; + + u64 eptp_controls; + u64 config_flags; + u16 tsc_frequency; + u8 reserved1[38]; + + u64 mrconfigid[6]; + u64 mrowner[6]; + u64 mrownerconfig[6]; + u64 reserved2[4]; + + union { + DECLARE_FLEX_ARRAY(struct tdx_cpuid_value, cpuid_values); + u8 reserved3[768]; + }; +} __packed __aligned(1024); + +/* + * Guest uses MAX_PA for GPAW when set. + * 0: GPA.SHARED bit is GPA[47] + * 1: GPA.SHARED bit is GPA[51] + */ +#define TDX_CONFIG_FLAGS_MAX_GPAW BIT_ULL(0) + +/* + * TDH.VP.ENTER, TDG.VP.VMCALL preserves RBP + * 0: RBP can be used for TDG.VP.VMCALL input. RBP is clobbered. + * 1: RBP can't be used for TDG.VP.VMCALL input. RBP is preserved. + */ +#define TDX_CONFIG_FLAGS_NO_RBP_MOD BIT_ULL(2) + + +/* + * TDX requires the frequency to be defined in units of 25MHz, which is the + * frequency of the core crystal clock on TDX-capable platforms, i.e. the TDX + * module can only program frequencies that are multiples of 25MHz. The + * frequency must be between 100mhz and 10ghz (inclusive). + */ +#define TDX_TSC_KHZ_TO_25MHZ(tsc_in_khz) ((tsc_in_khz) / (25 * 1000)) +#define TDX_TSC_25MHZ_TO_KHZ(tsc_in_25mhz) ((tsc_in_25mhz) * (25 * 1000)) +#define TDX_MIN_TSC_FREQUENCY_KHZ (100 * 1000) +#define TDX_MAX_TSC_FREQUENCY_KHZ (10 * 1000 * 1000) + +/* Additional Secure EPT entry information */ +#define TDX_SEPT_LEVEL_MASK GENMASK_ULL(2, 0) +#define TDX_SEPT_STATE_MASK GENMASK_ULL(15, 8) +#define TDX_SEPT_STATE_SHIFT 8 + +enum tdx_sept_entry_state { + TDX_SEPT_FREE = 0, + TDX_SEPT_BLOCKED = 1, + TDX_SEPT_PENDING = 2, + TDX_SEPT_PENDING_BLOCKED = 3, + TDX_SEPT_PRESENT = 4, +}; + +static inline u8 tdx_get_sept_level(u64 sept_entry_info) +{ + return sept_entry_info & TDX_SEPT_LEVEL_MASK; +} + +static inline u8 tdx_get_sept_state(u64 sept_entry_info) +{ + return (sept_entry_info & TDX_SEPT_STATE_MASK) >> TDX_SEPT_STATE_SHIFT; +} + +#define MD_FIELD_ID_FEATURES0_TOPOLOGY_ENUM BIT_ULL(20) + +/* + * TD scope metadata field ID. + */ +#define TD_MD_FIELD_ID_CPUID_VALUES 0x9410000300000000ULL + +#endif /* __KVM_X86_TDX_ARCH_H */ diff --git a/arch/x86/kvm/vmx/tdx_errno.h b/arch/x86/kvm/vmx/tdx_errno.h new file mode 100644 index 000000000000..6ff4672c4181 --- /dev/null +++ b/arch/x86/kvm/vmx/tdx_errno.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* architectural status code for SEAMCALL */ + +#ifndef __KVM_X86_TDX_ERRNO_H +#define __KVM_X86_TDX_ERRNO_H + +#define TDX_SEAMCALL_STATUS_MASK 0xFFFFFFFF00000000ULL + +/* + * TDX SEAMCALL Status Codes (returned in RAX) + */ +#define TDX_NON_RECOVERABLE_VCPU 0x4000000100000000ULL +#define TDX_NON_RECOVERABLE_TD 0x4000000200000000ULL +#define TDX_NON_RECOVERABLE_TD_NON_ACCESSIBLE 0x6000000500000000ULL +#define TDX_NON_RECOVERABLE_TD_WRONG_APIC_MODE 0x6000000700000000ULL +#define TDX_INTERRUPTED_RESUMABLE 0x8000000300000000ULL +#define TDX_OPERAND_INVALID 0xC000010000000000ULL +#define TDX_OPERAND_BUSY 0x8000020000000000ULL +#define TDX_PREVIOUS_TLB_EPOCH_BUSY 0x8000020100000000ULL +#define TDX_PAGE_METADATA_INCORRECT 0xC000030000000000ULL +#define TDX_VCPU_NOT_ASSOCIATED 0x8000070200000000ULL +#define TDX_KEY_GENERATION_FAILED 0x8000080000000000ULL +#define TDX_KEY_STATE_INCORRECT 0xC000081100000000ULL +#define TDX_KEY_CONFIGURED 0x0000081500000000ULL +#define TDX_NO_HKID_READY_TO_WBCACHE 0x0000082100000000ULL +#define TDX_FLUSHVP_NOT_DONE 0x8000082400000000ULL +#define TDX_EPT_WALK_FAILED 0xC0000B0000000000ULL +#define TDX_EPT_ENTRY_STATE_INCORRECT 0xC0000B0D00000000ULL +#define TDX_METADATA_FIELD_NOT_READABLE 0xC0000C0200000000ULL + +/* + * TDX module operand ID, appears in 31:0 part of error code as + * detail information + */ +#define TDX_OPERAND_ID_RCX 0x01 +#define TDX_OPERAND_ID_TDR 0x80 +#define TDX_OPERAND_ID_SEPT 0x92 +#define TDX_OPERAND_ID_TD_EPOCH 0xa9 + +#endif /* __KVM_X86_TDX_ERRNO_H */ diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 7c1996b433e2..b25625314658 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -140,6 +140,11 @@ static inline bool is_nm_fault(u32 intr_info) return is_exception_n(intr_info, NM_VECTOR); } +static inline bool is_ve_fault(u32 intr_info) +{ + return is_exception_n(intr_info, VE_VECTOR); +} + /* Undocumented: icebp/int1 */ static inline bool is_icebp(u32 intr_info) { diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h index 01936013428b..56fd150a6f24 100644 --- a/arch/x86/kvm/vmx/vmcs12.h +++ b/arch/x86/kvm/vmx/vmcs12.h @@ -188,12 +188,13 @@ struct __packed vmcs12 { }; /* - * VMCS12_REVISION is an arbitrary id that should be changed if the content or - * layout of struct vmcs12 is changed. MSR_IA32_VMX_BASIC returns this id, and - * VMPTRLD verifies that the VMCS region that L1 is loading contains this id. + * VMCS12_REVISION is KVM's arbitrary ID for the layout of struct vmcs12. KVM + * enumerates this value to L1 via MSR_IA32_VMX_BASIC, and checks the revision + * ID during nested VMPTRLD to verify that L1 is loading a VMCS that adhere's + * to KVM's virtual CPU definition. * - * IMPORTANT: Changing this value will break save/restore compatibility with - * older kvm releases. + * DO NOT change this value, as it will break save/restore compatibility with + * older KVM releases. */ #define VMCS12_REVISION 0x11e57ed0 @@ -206,7 +207,8 @@ struct __packed vmcs12 { #define VMCS12_SIZE KVM_STATE_NESTED_VMX_VMCS_SIZE /* - * For save/restore compatibility, the vmcs12 field offsets must not change. + * For save/restore compatibility, the vmcs12 field offsets must not change, + * although appending fields and/or filling gaps is obviously allowed. */ #define CHECK_OFFSET(field, loc) \ ASSERT_STRUCT_OFFSET(struct vmcs12, field, loc) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 22411f4aff53..b12414108cbf 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -46,6 +46,7 @@ #include <asm/perf_event.h> #include <asm/mmu_context.h> #include <asm/mshyperv.h> +#include <asm/msr.h> #include <asm/mwait.h> #include <asm/spec-ctrl.h> #include <asm/vmx.h> @@ -53,6 +54,7 @@ #include <trace/events/ipi.h> #include "capabilities.h" +#include "common.h" #include "cpuid.h" #include "hyperv.h" #include "kvm_onhyperv.h" @@ -68,10 +70,13 @@ #include "vmcs12.h" #include "vmx.h" #include "x86.h" +#include "x86_ops.h" #include "smm.h" #include "vmx_onhyperv.h" +#include "posted_intr.h" MODULE_AUTHOR("Qumranet"); +MODULE_DESCRIPTION("KVM support for VMX (Intel VT-x) extensions"); MODULE_LICENSE("GPL"); #ifdef MODULE @@ -214,9 +219,11 @@ module_param(ple_window_shrink, uint, 0444); static unsigned int ple_window_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX; module_param(ple_window_max, uint, 0444); -/* Default is SYSTEM mode, 1 for host-guest mode */ +/* Default is SYSTEM mode, 1 for host-guest mode (which is BROKEN) */ int __read_mostly pt_mode = PT_MODE_SYSTEM; +#ifdef CONFIG_BROKEN module_param(pt_mode, int, S_IRUGO); +#endif struct x86_pmu_lbr __ro_after_init vmx_lbr_caps; @@ -257,7 +264,7 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) return 0; } - if (host_arch_capabilities & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) { + if (kvm_host.arch_capabilities & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; return 0; } @@ -268,6 +275,7 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) case L1TF_MITIGATION_OFF: l1tf = VMENTER_L1D_FLUSH_NEVER; break; + case L1TF_MITIGATION_AUTO: case L1TF_MITIGATION_FLUSH_NOWARN: case L1TF_MITIGATION_FLUSH: case L1TF_MITIGATION_FLUSH_NOSMT: @@ -375,9 +383,9 @@ static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) if (!vmx->disable_fb_clear) return; - msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL); + msr = native_rdmsrq(MSR_IA32_MCU_OPT_CTRL); msr |= FB_CLEAR_DIS; - native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + native_wrmsrq(MSR_IA32_MCU_OPT_CTRL, msr); /* Cache the MSR value to avoid reading it later */ vmx->msr_ia32_mcu_opt_ctrl = msr; } @@ -388,7 +396,7 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) return; vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; - native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); + native_wrmsrq(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); } static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) @@ -402,7 +410,7 @@ static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) * and VM-Exit. */ vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && - (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && + (kvm_host.arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && !boot_cpu_has_bug(X86_BUG_MDS) && !boot_cpu_has_bug(X86_BUG_TAA); @@ -478,10 +486,9 @@ noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva) ext, vpid, gva); } -noinline void invept_error(unsigned long ext, u64 eptp, gpa_t gpa) +noinline void invept_error(unsigned long ext, u64 eptp) { - vmx_insn_failed("invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", - ext, eptp, gpa); + vmx_insn_failed("invept failed: ext=0x%lx eptp=%llx\n", ext, eptp); } static DEFINE_PER_CPU(struct vmcs *, vmxarea); @@ -522,16 +529,10 @@ static const struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; -static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) -{ - vmx->segment_cache.bitmask = 0; -} static unsigned long host_idt_base; #if IS_ENABLED(CONFIG_HYPERV) -static struct kvm_x86_ops vmx_x86_ops __initdata; - static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); @@ -581,9 +582,8 @@ static __init void hv_init_evmcs(void) } if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) - vmx_x86_ops.enable_l2_tlb_flush + vt_x86_ops.enable_l2_tlb_flush = hv_enable_l2_tlb_flush; - } else { enlightened_vmcs = false; } @@ -755,7 +755,7 @@ fault: return -EIO; } -static void vmx_emergency_disable(void) +void vmx_emergency_disable_virtualization_cpu(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; @@ -874,6 +874,12 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); /* + * #VE isn't used for VMX. To test against unexpected changes + * related to #VE for VMX, intercept unexpected #VE and warn on it. + */ + if (IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE)) + eb |= 1u << VE_VECTOR; + /* * Guest access to VMware backdoor ports could legitimately * trigger #GP because of TSS I/O permission bitmap. * We intercept those #GP and allow access to them anyway @@ -1060,7 +1066,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, * provide that period, so a CPU could write host's record into * guest's memory. */ - wrmsrl(MSR_IA32_PEBS_ENABLE, 0); + wrmsrq(MSR_IA32_PEBS_ENABLE, 0); } i = vmx_find_loadstore_msr_slot(&m->guest, msr); @@ -1118,12 +1124,12 @@ static bool update_transition_efer(struct vcpu_vmx *vmx) * atomically, since it's faster than switching it manually. */ if (cpu_has_load_ia32_efer() || - (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { + (enable_ept && ((vmx->vcpu.arch.efer ^ kvm_host.efer) & EFER_NX))) { if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; - if (guest_efer != host_efer) + if (guest_efer != kvm_host.efer) add_atomic_switch_msr(vmx, MSR_EFER, - guest_efer, host_efer, false); + guest_efer, kvm_host.efer, false); else clear_atomic_switch_msr(vmx, MSR_EFER); return false; @@ -1136,7 +1142,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx) clear_atomic_switch_msr(vmx, MSR_EFER); guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; + guest_efer |= kvm_host.efer & ignore_bits; vmx->guest_uret_msrs[i].data = guest_efer; vmx->guest_uret_msrs[i].mask = ~ignore_bits; @@ -1189,13 +1195,13 @@ static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range) { u32 i; - wrmsrl(MSR_IA32_RTIT_STATUS, ctx->status); - wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); - wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); - wrmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); + wrmsrq(MSR_IA32_RTIT_STATUS, ctx->status); + wrmsrq(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); + wrmsrq(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); + wrmsrq(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); for (i = 0; i < addr_range; i++) { - wrmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); - wrmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); + wrmsrq(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); + wrmsrq(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); } } @@ -1203,13 +1209,13 @@ static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range) { u32 i; - rdmsrl(MSR_IA32_RTIT_STATUS, ctx->status); - rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); - rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); - rdmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); + rdmsrq(MSR_IA32_RTIT_STATUS, ctx->status); + rdmsrq(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); + rdmsrq(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); + rdmsrq(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); for (i = 0; i < addr_range; i++) { - rdmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); - rdmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); + rdmsrq(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); + rdmsrq(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); } } @@ -1222,9 +1228,9 @@ static void pt_guest_enter(struct vcpu_vmx *vmx) * GUEST_IA32_RTIT_CTL is already set in the VMCS. * Save host state before VM entry. */ - rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); + rdmsrq(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { - wrmsrl(MSR_IA32_RTIT_CTL, 0); + wrmsrq(MSR_IA32_RTIT_CTL, 0); pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.num_address_ranges); pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.num_address_ranges); } @@ -1245,7 +1251,7 @@ static void pt_guest_exit(struct vcpu_vmx *vmx) * i.e. RTIT_CTL is always cleared on VM-Exit. Restore it if necessary. */ if (vmx->pt_desc.host.ctl) - wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); + wrmsrq(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); } void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, @@ -1278,6 +1284,7 @@ void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vcpu_vt *vt = to_vt(vcpu); struct vmcs_host_state *host_state; #ifdef CONFIG_X86_64 int cpu = raw_smp_processor_id(); @@ -1306,7 +1313,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) if (vmx->nested.need_vmcs12_to_shadow_sync) nested_sync_vmcs12_to_shadow(vcpu); - if (vmx->guest_state_loaded) + if (vt->guest_state_loaded) return; host_state = &vmx->loaded_vmcs->host_state; @@ -1327,15 +1334,15 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) fs_sel = current->thread.fsindex; gs_sel = current->thread.gsindex; fs_base = current->thread.fsbase; - vmx->msr_host_kernel_gs_base = current->thread.gsbase; + vt->msr_host_kernel_gs_base = current->thread.gsbase; } else { savesegment(fs, fs_sel); savesegment(gs, gs_sel); fs_base = read_msr(MSR_FS_BASE); - vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); + vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); } - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + wrmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #else savesegment(fs, fs_sel); savesegment(gs, gs_sel); @@ -1344,14 +1351,14 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) #endif vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); - vmx->guest_state_loaded = true; + vt->guest_state_loaded = true; } static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) { struct vmcs_host_state *host_state; - if (!vmx->guest_state_loaded) + if (!vmx->vt.guest_state_loaded) return; host_state = &vmx->loaded_vmcs->host_state; @@ -1359,7 +1366,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) ++vmx->vcpu.stat.host_state_reload; #ifdef CONFIG_X86_64 - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + rdmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #endif if (host_state->ldt_sel || (host_state->gs_sel & 7)) { kvm_load_ldt(host_state->ldt_sel); @@ -1379,10 +1386,10 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) #endif invalidate_tss_limit(); #ifdef CONFIG_X86_64 - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); + wrmsrq(MSR_KERNEL_GS_BASE, vmx->vt.msr_host_kernel_gs_base); #endif load_fixmap_gdt(raw_smp_processor_id()); - vmx->guest_state_loaded = false; + vmx->vt.guest_state_loaded = false; vmx->guest_uret_msrs_loaded = false; } @@ -1390,8 +1397,8 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) { preempt_disable(); - if (vmx->guest_state_loaded) - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + if (vmx->vt.guest_state_loaded) + rdmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); preempt_enable(); return vmx->msr_guest_kernel_gs_base; } @@ -1399,13 +1406,45 @@ static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data) { preempt_disable(); - if (vmx->guest_state_loaded) - wrmsrl(MSR_KERNEL_GS_BASE, data); + if (vmx->vt.guest_state_loaded) + wrmsrq(MSR_KERNEL_GS_BASE, data); preempt_enable(); vmx->msr_guest_kernel_gs_base = data; } #endif +static void grow_ple_window(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned int old = vmx->ple_window; + + vmx->ple_window = __grow_ple_window(old, ple_window, + ple_window_grow, + ple_window_max); + + if (vmx->ple_window != old) { + vmx->ple_window_dirty = true; + trace_kvm_ple_window_update(vcpu->vcpu_id, + vmx->ple_window, old); + } +} + +static void shrink_ple_window(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned int old = vmx->ple_window; + + vmx->ple_window = __shrink_ple_window(old, ple_window, + ple_window_shrink, + ple_window); + + if (vmx->ple_window != old) { + vmx->ple_window_dirty = true; + trace_kvm_ple_window_update(vcpu->vcpu_id, + vmx->ple_window, old); + } +} + void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, struct loaded_vmcs *buddy) { @@ -1442,7 +1481,8 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, * performs IBPB on nested VM-Exit (a single nested transition * may switch the active VMCS multiple times). */ - if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)) + if (static_branch_likely(&switch_vcpu_ibpb) && + (!buddy || WARN_ON_ONCE(buddy->vmcs != prev))) indirect_branch_prediction_barrier(); } @@ -1477,18 +1517,17 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. */ -static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); + if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm)) + shrink_ple_window(vcpu); vmx_vcpu_load_vmcs(vcpu, cpu, NULL); vmx_vcpu_pi_load(vcpu, cpu); - - vmx->host_debugctlmsr = get_debugctlmsr(); } -static void vmx_vcpu_put(struct kvm_vcpu *vcpu) +void vmx_vcpu_put(struct kvm_vcpu *vcpu) { vmx_vcpu_pi_put(vcpu); @@ -1544,10 +1583,10 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) vmcs_writel(GUEST_RFLAGS, rflags); if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) - vmx->emulation_required = vmx_emulation_required(vcpu); + vmx->vt.emulation_required = vmx_emulation_required(vcpu); } -static bool vmx_get_if_flag(struct kvm_vcpu *vcpu) +bool vmx_get_if_flag(struct kvm_vcpu *vcpu) { return vmx_get_rflags(vcpu) & X86_EFLAGS_IF; } @@ -1598,7 +1637,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) * result in a #GP unless the same write also clears TraceEn. */ if ((vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) && - ((vmx->pt_desc.guest.ctl ^ data) & ~RTIT_CTL_TRACEEN)) + (data & RTIT_CTL_TRACEEN) && + data != vmx->pt_desc.guest.ctl) return 1; /* @@ -1653,8 +1693,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } -static int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does @@ -1663,16 +1703,22 @@ static int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * 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) { + if (vmx_get_exit_reason(vcpu).enclave_mode) { kvm_queue_exception(vcpu, UD_VECTOR); return X86EMUL_PROPAGATE_FAULT; } + + /* Check that emulation is possible during event vectoring */ + if ((to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && + !kvm_can_emulate_event_vectoring(emul_type)) + return X86EMUL_UNHANDLEABLE_VECTORING; + return X86EMUL_CONTINUE; } static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { - union vmx_exit_reason exit_reason = to_vmx(vcpu)->exit_reason; + union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu); unsigned long rip, orig_rip; u32 instr_len; @@ -1738,7 +1784,7 @@ rip_updated: * Recognizes a pending MTF VM-exit and records the nested state for later * delivery. */ -static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) +void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -1769,7 +1815,7 @@ static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) } } -static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) +int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) { vmx_update_emulated_instruction(vcpu); return skip_emulated_instruction(vcpu); @@ -1788,7 +1834,7 @@ static void vmx_clear_hlt(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); } -static void vmx_inject_exception(struct kvm_vcpu *vcpu) +void vmx_inject_exception(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; @@ -1819,7 +1865,7 @@ static void vmx_inject_exception(struct kvm_vcpu *vcpu) return; } - WARN_ON_ONCE(vmx->emulation_required); + WARN_ON_ONCE(vmx->vt.emulation_required); if (kvm_exception_is_soft(ex->vector)) { vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, @@ -1870,8 +1916,8 @@ static void vmx_setup_uret_msrs(struct vcpu_vmx *vmx) vmx_setup_uret_msr(vmx, MSR_EFER, update_transition_efer(vmx)); vmx_setup_uret_msr(vmx, MSR_TSC_AUX, - guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDPID)); + guest_cpu_cap_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || + guest_cpu_cap_has(&vmx->vcpu, X86_FEATURE_RDPID)); /* * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations of new @@ -1909,12 +1955,12 @@ u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) return kvm_caps.default_tsc_scaling_ratio; } -static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu) +void vmx_write_tsc_offset(struct kvm_vcpu *vcpu) { vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); } -static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu) +void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu) { vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); } @@ -1957,15 +2003,15 @@ static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, return !(msr->data & ~valid_bits); } -static int vmx_get_msr_feature(struct kvm_msr_entry *msr) +int vmx_get_feature_msr(u32 msr, u64 *data) { - switch (msr->index) { + switch (msr) { case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!nested) return 1; - return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data); + return vmx_get_vmx_msr(&vmcs_config.nested, msr, data); default: - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } } @@ -1974,7 +2020,7 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_uret_msr *msr; @@ -2024,7 +2070,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) + !guest_cpu_cap_has(vcpu, X86_FEATURE_MPX))) return 1; msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; @@ -2040,13 +2086,13 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SGXLEPUBKEYHASH0 ... MSR_IA32_SGXLEPUBKEYHASH3: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC)) + !guest_cpu_cap_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 KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: - if (!guest_can_use(vcpu, X86_FEATURE_VMX)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return 1; if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data)) @@ -2059,7 +2105,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * sanity checking and refuse to boot. Filter all unsupported * features out. */ - if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu)) + if (!msr_info->host_initiated && guest_cpu_cap_has_evmcs(vcpu)) nested_evmcs_filter_control_msr(vcpu, msr_info->index, &msr_info->data); #endif @@ -2129,7 +2175,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, u64 data) { #ifdef CONFIG_X86_64 - if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return (u32)data; #endif return (unsigned long)data; @@ -2140,7 +2186,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated u64 debugctl = 0; if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) && - (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) + (host_initiated || guest_cpu_cap_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; if ((kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT) && @@ -2155,7 +2201,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_uret_msr *msr; @@ -2244,9 +2290,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) + !guest_cpu_cap_has(vcpu, X86_FEATURE_MPX))) return 1; - if (is_noncanonical_address(data & PAGE_MASK, vcpu) || + if (is_noncanonical_msr_address(data & PAGE_MASK, vcpu) || (data & MSR_IA32_BNDCFGS_RSVD)) return 1; @@ -2346,7 +2392,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * behavior, but it's close enough. */ if (!msr_info->host_initiated && - (!guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC) || + (!guest_cpu_cap_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; @@ -2356,7 +2402,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!msr_info->host_initiated) return 1; /* they are read-only */ - if (!guest_can_use(vcpu, X86_FEATURE_VMX)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_RTIT_CTL: @@ -2411,7 +2457,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; if (index >= 2 * vmx->pt_desc.num_address_ranges) return 1; - if (is_noncanonical_address(data, vcpu)) + if (is_noncanonical_msr_address(data, vcpu)) return 1; if (index % 2) vmx->pt_desc.guest.addr_b[index / 2] = data; @@ -2419,8 +2465,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmx->pt_desc.guest.addr_a[index / 2] = data; break; case MSR_IA32_PERF_CAPABILITIES: - if (data && !vcpu_to_pmu(vcpu)->version) - return 1; if (data & PMU_CAP_LBR_FMT) { if ((data & PMU_CAP_LBR_FMT) != (kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT)) @@ -2432,9 +2476,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if ((data & PERF_CAP_PEBS_MASK) != (kvm_caps.supported_perf_cap & PERF_CAP_PEBS_MASK)) return 1; - if (!guest_cpuid_has(vcpu, X86_FEATURE_DS)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_DS)) return 1; - if (!guest_cpuid_has(vcpu, X86_FEATURE_DTES64)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_DTES64)) return 1; if (!cpuid_model_is_consistent(vcpu)) return 1; @@ -2458,7 +2502,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return ret; } -static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) +void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { unsigned long guest_owned_bits; @@ -2512,30 +2556,6 @@ static bool cpu_has_sgx(void) return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0)); } -/* - * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they - * can't be used due to errata where VM Exit may incorrectly clear - * IA32_PERF_GLOBAL_CTRL[34:32]. Work around the errata by using the - * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL. - */ -static bool cpu_has_perf_global_ctrl_bug(void) -{ - if (boot_cpu_data.x86 == 0x6) { - switch (boot_cpu_data.x86_model) { - case INTEL_FAM6_NEHALEM_EP: /* AAK155 */ - case INTEL_FAM6_NEHALEM: /* AAP115 */ - case INTEL_FAM6_WESTMERE: /* AAT100 */ - case INTEL_FAM6_WESTMERE_EP: /* BC86,AAY89,BD102 */ - case INTEL_FAM6_NEHALEM_EX: /* BA97 */ - return true; - default: - break; - } - } - - return false; -} - static int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result) { u32 vmx_msr_low, vmx_msr_high; @@ -2558,23 +2578,50 @@ static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) { u64 allowed; - rdmsrl(msr, allowed); + rdmsrq(msr, allowed); return ctl_opt & allowed; } +#define vmx_check_entry_exit_pairs(pairs, entry_controls, exit_controls) \ +({ \ + int i, r = 0; \ + \ + BUILD_BUG_ON(sizeof(pairs[0].entry_control) != sizeof(entry_controls)); \ + BUILD_BUG_ON(sizeof(pairs[0].exit_control) != sizeof(exit_controls)); \ + \ + for (i = 0; i < ARRAY_SIZE(pairs); i++) { \ + typeof(entry_controls) n_ctrl = pairs[i].entry_control; \ + typeof(exit_controls) x_ctrl = pairs[i].exit_control; \ + \ + if (!(entry_controls & n_ctrl) == !(exit_controls & x_ctrl)) \ + continue; \ + \ + pr_warn_once("Inconsistent VM-Entry/VM-Exit pair, " \ + "entry = %llx (%llx), exit = %llx (%llx)\n", \ + (u64)(entry_controls & n_ctrl), (u64)n_ctrl, \ + (u64)(exit_controls & x_ctrl), (u64)x_ctrl); \ + \ + if (error_on_inconsistent_vmcs_config) \ + r = -EIO; \ + \ + entry_controls &= ~n_ctrl; \ + exit_controls &= ~x_ctrl; \ + } \ + r; \ +}) + static int setup_vmcs_config(struct vmcs_config *vmcs_conf, struct vmx_capability *vmx_cap) { - u32 vmx_msr_low, vmx_msr_high; u32 _pin_based_exec_control = 0; u32 _cpu_based_exec_control = 0; u32 _cpu_based_2nd_exec_control = 0; u64 _cpu_based_3rd_exec_control = 0; u32 _vmexit_control = 0; u32 _vmentry_control = 0; + u64 basic_msr; u64 misc_msr; - int i; /* * LOAD/SAVE_DEBUG_CONTROLS are absent because both are mandatory. @@ -2606,6 +2653,9 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, &_cpu_based_2nd_exec_control)) return -EIO; } + if (!IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE)) + _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; + #ifndef CONFIG_X86_64 if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) @@ -2630,6 +2680,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, return -EIO; vmx_cap->ept = 0; + _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; } if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) && vmx_cap->vpid) { @@ -2674,46 +2725,54 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, &_vmentry_control)) return -EIO; - for (i = 0; i < ARRAY_SIZE(vmcs_entry_exit_pairs); i++) { - u32 n_ctrl = vmcs_entry_exit_pairs[i].entry_control; - u32 x_ctrl = vmcs_entry_exit_pairs[i].exit_control; - - if (!(_vmentry_control & n_ctrl) == !(_vmexit_control & x_ctrl)) - continue; - - pr_warn_once("Inconsistent VM-Entry/VM-Exit pair, entry = %x, exit = %x\n", - _vmentry_control & n_ctrl, _vmexit_control & x_ctrl); - - if (error_on_inconsistent_vmcs_config) - return -EIO; + if (vmx_check_entry_exit_pairs(vmcs_entry_exit_pairs, + _vmentry_control, _vmexit_control)) + return -EIO; - _vmentry_control &= ~n_ctrl; - _vmexit_control &= ~x_ctrl; + /* + * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they + * can't be used due to an errata where VM Exit may incorrectly clear + * IA32_PERF_GLOBAL_CTRL[34:32]. Workaround the errata by using the + * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL. + */ + switch (boot_cpu_data.x86_vfm) { + case INTEL_NEHALEM_EP: /* AAK155 */ + case INTEL_NEHALEM: /* AAP115 */ + case INTEL_WESTMERE: /* AAT100 */ + case INTEL_WESTMERE_EP: /* BC86,AAY89,BD102 */ + case INTEL_NEHALEM_EX: /* BA97 */ + _vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + _vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + pr_warn_once("VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " + "does not work properly. Using workaround\n"); + break; + default: + break; } - rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); + rdmsrq(MSR_IA32_VMX_BASIC, basic_msr); /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ - if ((vmx_msr_high & 0x1fff) > PAGE_SIZE) + if (vmx_basic_vmcs_size(basic_msr) > PAGE_SIZE) return -EIO; #ifdef CONFIG_X86_64 - /* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */ - if (vmx_msr_high & (1u<<16)) + /* + * KVM expects to be able to shove all legal physical addresses into + * VMCS fields for 64-bit kernels, and per the SDM, "This bit is always + * 0 for processors that support Intel 64 architecture". + */ + if (basic_msr & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EIO; #endif /* Require Write-Back (WB) memory type for VMCS accesses. */ - if (((vmx_msr_high >> 18) & 15) != 6) + if (vmx_basic_vmcs_mem_type(basic_msr) != X86_MEMTYPE_WB) return -EIO; - rdmsrl(MSR_IA32_VMX_MISC, misc_msr); - - vmcs_conf->size = vmx_msr_high & 0x1fff; - vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; - - vmcs_conf->revision_id = vmx_msr_low; + rdmsrq(MSR_IA32_VMX_MISC, misc_msr); + vmcs_conf->basic = basic_msr; vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control; @@ -2759,7 +2818,7 @@ static bool kvm_is_vmx_supported(void) return supported; } -static int vmx_check_processor_compat(void) +int vmx_check_processor_compat(void) { int cpu = raw_smp_processor_id(); struct vmcs_config vmcs_conf; @@ -2795,13 +2854,13 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer) fault: WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", - rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); + rdmsrq_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); cr4_clear_bits(X86_CR4_VMXE); return -EFAULT; } -static int vmx_hardware_enable(void) +int vmx_enable_virtualization_cpu(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); @@ -2825,9 +2884,6 @@ static int vmx_hardware_enable(void) return r; } - if (enable_ept) - ept_sync_global(); - return 0; } @@ -2841,7 +2897,7 @@ static void vmclear_local_loaded_vmcss(void) __loaded_vmcs_clear(v); } -static void vmx_hardware_disable(void) +void vmx_disable_virtualization_cpu(void) { vmclear_local_loaded_vmcss(); @@ -2863,13 +2919,13 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) if (!pages) return NULL; vmcs = page_address(pages); - memset(vmcs, 0, vmcs_config.size); + memset(vmcs, 0, vmx_basic_vmcs_size(vmcs_config.basic)); /* KVM supports Enlightened VMCS v1 only */ if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = KVM_EVMCS_VERSION; else - vmcs->hdr.revision_id = vmcs_config.revision_id; + vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); if (shadow) vmcs->hdr.shadow_vmcs = 1; @@ -2962,7 +3018,7 @@ static __init int alloc_kvm_area(void) * physical CPU. */ if (kvm_is_using_evmcs()) - vmcs->hdr.revision_id = vmcs_config.revision_id; + vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); per_cpu(vmxarea, cpu) = vmcs; } @@ -3155,7 +3211,7 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif -static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) +void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3180,12 +3236,12 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu)) + if (is_guest_mode(vcpu) && nested_cpu_has_vpid(get_vmcs12(vcpu))) return nested_get_vpid02(vcpu); return to_vmx(vcpu)->vpid; } -static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) +void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; u64 root_hpa = mmu->root.hpa; @@ -3201,7 +3257,7 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) vpid_sync_context(vmx_get_current_vpid(vcpu)); } -static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) +void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) { /* * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in @@ -3210,7 +3266,7 @@ static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr); } -static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) +void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) { /* * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a @@ -3255,7 +3311,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) #define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \ CPU_BASED_CR3_STORE_EXITING) -static bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { if (is_guest_mode(vcpu)) return nested_guest_cr0_valid(vcpu, cr0); @@ -3352,7 +3408,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } /* depends on vcpu->arch.cr0 to be set to a new value */ - vmx->emulation_required = vmx_emulation_required(vcpu); + vmx->vt.emulation_required = vmx_emulation_required(vcpu); } static int vmx_get_max_ept_level(void) @@ -3376,8 +3432,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) return eptp; } -static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, - int root_level) +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; @@ -3406,8 +3461,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, vmcs_writel(GUEST_CR3, guest_cr3); } - -static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { /* * We operate under the default treatment of SMM, so VMX cannot be @@ -3484,7 +3538,7 @@ void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vmcs_writel(GUEST_CR4, hw_cr4); if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE)) - kvm_update_cpuid_runtime(vcpu); + vcpu->arch.cpuid_dynamic_bits_dirty = true; } void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) @@ -3523,7 +3577,7 @@ void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) var->g = (ar >> 15) & 1; } -static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) +u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) { struct kvm_segment s; @@ -3534,16 +3588,29 @@ static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) return vmx_read_guest_seg_base(to_vmx(vcpu), seg); } -int vmx_get_cpl(struct kvm_vcpu *vcpu) +static int __vmx_get_cpl(struct kvm_vcpu *vcpu, bool no_cache) { struct vcpu_vmx *vmx = to_vmx(vcpu); + int ar; if (unlikely(vmx->rmode.vm86_active)) return 0; - else { - int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); - return VMX_AR_DPL(ar); - } + + if (no_cache) + ar = vmcs_read32(GUEST_SS_AR_BYTES); + else + ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); + return VMX_AR_DPL(ar); +} + +int vmx_get_cpl(struct kvm_vcpu *vcpu) +{ + return __vmx_get_cpl(vcpu, false); +} + +int vmx_get_cpl_no_cache(struct kvm_vcpu *vcpu) +{ + return __vmx_get_cpl(vcpu, true); } static u32 vmx_segment_access_rights(struct kvm_segment *var) @@ -3600,14 +3667,14 @@ void __vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var)); } -static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) +void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { __vmx_set_segment(vcpu, var, seg); - to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); + to_vmx(vcpu)->vt.emulation_required = vmx_emulation_required(vcpu); } -static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) +void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS); @@ -3615,25 +3682,25 @@ static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) *l = (ar >> 13) & 1; } -static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { dt->size = vmcs_read32(GUEST_IDTR_LIMIT); dt->address = vmcs_readl(GUEST_IDTR_BASE); } -static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { vmcs_write32(GUEST_IDTR_LIMIT, dt->size); vmcs_writel(GUEST_IDTR_BASE, dt->address); } -static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { dt->size = vmcs_read32(GUEST_GDTR_LIMIT); dt->address = vmcs_readl(GUEST_GDTR_BASE); } -static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { vmcs_write32(GUEST_GDTR_LIMIT, dt->size); vmcs_writel(GUEST_GDTR_BASE, dt->address); @@ -4101,27 +4168,7 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu) } } -static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - void *vapic_page; - u32 vppr; - int rvi; - - if (WARN_ON_ONCE(!is_guest_mode(vcpu)) || - !nested_cpu_has_vid(get_vmcs12(vcpu)) || - WARN_ON_ONCE(!vmx->nested.virtual_apic_map.gfn)) - return false; - - rvi = vmx_get_rvi(); - - vapic_page = vmx->nested.virtual_apic_map.hva; - vppr = *((u32 *)(vapic_page + APIC_PROCPRI)); - - return ((rvi & 0xf0) > (vppr & 0xf0)); -} - -static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu) +void vmx_msr_filter_changed(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 i; @@ -4152,55 +4199,18 @@ static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu) pt_update_intercept_for_msr(vcpu); } -static inline void kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, - int pi_vec) -{ -#ifdef CONFIG_SMP - if (vcpu->mode == IN_GUEST_MODE) { - /* - * The vector of the virtual has already been set in the PIR. - * Send a notification event to deliver the virtual interrupt - * unless the vCPU is the currently running vCPU, i.e. the - * event is being sent from a fastpath VM-Exit handler, in - * which case the PIR will be synced to the vIRR before - * re-entering the guest. - * - * When the target is not the running vCPU, the following - * possibilities emerge: - * - * Case 1: vCPU stays in non-root mode. Sending a notification - * event posts the interrupt to the vCPU. - * - * Case 2: vCPU exits to root mode and is still runnable. The - * PIR will be synced to the vIRR before re-entering the guest. - * Sending a notification event is ok as the host IRQ handler - * will ignore the spurious event. - * - * Case 3: vCPU exits to root mode and is blocked. vcpu_block() - * has already synced PIR to vIRR and never blocks the vCPU if - * the vIRR is not empty. Therefore, a blocked vCPU here does - * not wait for any requested interrupts in PIR, and sending a - * notification event also results in a benign, spurious event. - */ - - if (vcpu != kvm_get_running_vcpu()) - __apic_send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec); - return; - } -#endif - /* - * The vCPU isn't in the guest; wake the vCPU in case it is blocking, - * otherwise do nothing as KVM will grab the highest priority pending - * IRQ via ->sync_pir_to_irr() in vcpu_enter_guest(). - */ - kvm_vcpu_wake_up(vcpu); -} - static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * DO NOT query the vCPU's vmcs12, as vmcs12 is dynamically allocated + * and freed, and must not be accessed outside of vcpu->mutex. The + * vCPU's cached PI NV is valid if and only if posted interrupts + * enabled in its vmcs12, i.e. checking the vector also checks that + * L1 has enabled posted interrupts for L2. + */ if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { /* @@ -4237,7 +4247,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, */ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { - struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vcpu_vt *vt = to_vt(vcpu); int r; r = vmx_deliver_nested_posted_interrupt(vcpu, vector); @@ -4248,25 +4258,12 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (!vcpu->arch.apic->apicv_active) return -1; - if (pi_test_and_set_pir(vector, &vmx->pi_desc)) - return 0; - - /* If a previous notification has sent the IPI, nothing to do. */ - if (pi_test_and_set_on(&vmx->pi_desc)) - return 0; - - /* - * The implied barrier in pi_test_and_set_on() pairs with the smp_mb_*() - * after setting vcpu->mode in vcpu_enter_guest(), thus the vCPU is - * guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a - * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE. - */ - kvm_vcpu_trigger_posted_interrupt(vcpu, POSTED_INTR_VECTOR); + __vmx_deliver_posted_interrupt(vcpu, &vt->pi_desc, vector); return 0; } -static void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, - int trig_mode, int vector) +void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) { struct kvm_vcpu *vcpu = apic->vcpu; @@ -4341,7 +4338,7 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) if (!IS_ENABLED(CONFIG_IA32_EMULATION) && !IS_ENABLED(CONFIG_X86_32)) vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); - rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl); + rdmsrq(MSR_IA32_SYSENTER_EIP, tmpl); vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) { @@ -4350,7 +4347,7 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) } if (cpu_has_load_ia32_efer()) - vmcs_write64(HOST_IA32_EFER, host_efer); + vmcs_write64(HOST_IA32_EFER, kvm_host.efer); } void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) @@ -4399,9 +4396,6 @@ static u32 vmx_vmentry_ctrl(void) VM_ENTRY_LOAD_IA32_EFER | VM_ENTRY_IA32E_MODE); - if (cpu_has_perf_global_ctrl_bug()) - vmentry_ctrl &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; - return vmentry_ctrl; } @@ -4419,16 +4413,12 @@ static u32 vmx_vmexit_ctrl(void) if (vmx_pt_mode_is_system()) vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | VM_EXIT_CLEAR_IA32_RTIT_CTL); - - if (cpu_has_perf_global_ctrl_bug()) - vmexit_ctrl &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; - /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ return vmexit_ctrl & ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); } -static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4538,7 +4528,8 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, * Update the nested MSR settings so that a nested VMM can/can't set * controls for features that are/aren't exposed to the guest. */ - if (nested) { + if (nested && + kvm_check_has_quirk(vmx->vcpu.kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) { /* * All features that can be added or removed to VMX MSRs must * be supported in the first place for nested virtualization. @@ -4564,10 +4555,7 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, bool __enabled; \ \ if (cpu_has_vmx_##name()) { \ - if (kvm_is_governed_feature(X86_FEATURE_##feat_name)) \ - __enabled = guest_can_use(__vcpu, X86_FEATURE_##feat_name); \ - else \ - __enabled = guest_cpuid_has(__vcpu, X86_FEATURE_##feat_name); \ + __enabled = guest_cpu_cap_has(__vcpu, X86_FEATURE_##feat_name); \ vmx_adjust_secondary_exec_control(vmx, exec_control, SECONDARY_EXEC_##ctrl_name,\ __enabled, exiting); \ } \ @@ -4594,6 +4582,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; + exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; enable_unrestricted_guest = 0; } if (!enable_unrestricted_guest) @@ -4642,8 +4631,8 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) */ if (cpu_has_vmx_rdtscp()) { bool rdpid_or_rdtscp_enabled = - guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID); vmx_adjust_secondary_exec_control(vmx, &exec_control, SECONDARY_EXEC_ENABLE_RDTSCP, @@ -4692,7 +4681,7 @@ static int vmx_alloc_ipiv_pid_table(struct kvm *kvm) return 0; } -static int vmx_vcpu_precreate(struct kvm *kvm) +int vmx_vcpu_precreate(struct kvm *kvm) { return vmx_alloc_ipiv_pid_table(kvm); } @@ -4717,8 +4706,12 @@ static void init_vmcs(struct vcpu_vmx *vmx) exec_controls_set(vmx, vmx_exec_control(vmx)); - if (cpu_has_secondary_exec_ctrls()) + if (cpu_has_secondary_exec_ctrls()) { secondary_exec_controls_set(vmx, vmx_secondary_exec_control(vmx)); + if (vmx->ve_info) + vmcs_write64(VE_INFORMATION_ADDRESS, + __pa(vmx->ve_info)); + } if (cpu_has_tertiary_exec_ctrls()) tertiary_exec_controls_set(vmx, vmx_tertiary_exec_control(vmx)); @@ -4732,7 +4725,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmcs_write16(GUEST_INTR_STATUS, 0); vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); - vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc))); + vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->vt.pi_desc))); } if (vmx_can_use_ipiv(&vmx->vcpu)) { @@ -4789,7 +4782,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) if (enable_pml) { vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX); } vmx_write_encls_bitmap(&vmx->vcpu, NULL); @@ -4823,7 +4816,8 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu) init_vmcs(vmx); - if (nested) + if (nested && + kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) memcpy(&vmx->nested.msrs, &vmcs_config.nested, sizeof(vmx->nested.msrs)); vcpu_setup_sgx_lepubkeyhash(vcpu); @@ -4836,18 +4830,19 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; #endif - vcpu->arch.microcode_version = 0x100000000ULL; + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) + vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; /* * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR * or POSTED_INTR_WAKEUP_VECTOR. */ - vmx->pi_desc.nv = POSTED_INTR_VECTOR; - vmx->pi_desc.sn = 1; + vmx->vt.pi_desc.nv = POSTED_INTR_VECTOR; + __pi_set_sn(&vmx->vt.pi_desc); } -static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) +void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4862,9 +4857,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx->hv_deadline_tsc = -1; kvm_set_cr8(vcpu, 0); - vmx_segment_cache_clear(vmx); - kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS); - seg_setup(VCPU_SREG_CS); vmcs_write16(GUEST_CS_SELECTOR, 0xf000); vmcs_writel(GUEST_CS_BASE, 0xffff0000ul); @@ -4891,6 +4883,9 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_writel(GUEST_IDTR_BASE, 0); vmcs_write32(GUEST_IDTR_LIMIT, 0xffff); + vmx_segment_cache_clear(vmx); + kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS); + vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0); @@ -4906,12 +4901,12 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx_update_fb_clear_dis(vcpu, vmx); } -static void vmx_enable_irq_window(struct kvm_vcpu *vcpu) +void vmx_enable_irq_window(struct kvm_vcpu *vcpu) { exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); } -static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) +void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) { if (!enable_vnmi || vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { @@ -4922,7 +4917,7 @@ static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); } -static void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) +void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { struct vcpu_vmx *vmx = to_vmx(vcpu); uint32_t intr; @@ -4950,7 +4945,7 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) vmx_clear_hlt(vcpu); } -static void vmx_inject_nmi(struct kvm_vcpu *vcpu) +void vmx_inject_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -5028,7 +5023,7 @@ bool vmx_nmi_blocked(struct kvm_vcpu *vcpu) GUEST_INTR_STATE_NMI)); } -static int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; @@ -5040,17 +5035,22 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !vmx_nmi_blocked(vcpu); } +bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu) +{ + return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || + (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); +} + bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) return false; - return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || - (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); + return __vmx_interrupt_blocked(vcpu); } -static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) +int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; @@ -5065,7 +5065,7 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !vmx_interrupt_blocked(vcpu); } -static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) +int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { void __user *ret; @@ -5085,7 +5085,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) return init_rmode_tss(kvm, ret); } -static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) +int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { to_kvm_vmx(kvm)->ept_identity_map_addr = ident_addr; return 0; @@ -5173,6 +5173,12 @@ bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu) (kvm_get_rflags(vcpu) & X86_EFLAGS_AC); } +static bool is_xfd_nm_fault(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.guest_fpu.fpstate->xfd && + !kvm_is_cr0_bit_set(vcpu, X86_CR0_TS); +} + static int handle_exception_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -5199,13 +5205,24 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) * point. */ if (is_nm_fault(intr_info)) { - kvm_queue_exception(vcpu, NM_VECTOR); + kvm_queue_exception_p(vcpu, NM_VECTOR, + is_xfd_nm_fault(vcpu) ? vcpu->arch.guest_fpu.xfd_err : 0); return 1; } if (is_invalid_opcode(intr_info)) return handle_ud(vcpu); + if (WARN_ON_ONCE(is_ve_fault(intr_info))) { + struct vmx_ve_information *ve_info = vmx->ve_info; + + WARN_ONCE(ve_info->exit_reason != EXIT_REASON_EPT_VIOLATION, + "Unexpected #VE on VM-Exit reason 0x%x", ve_info->exit_reason); + dump_vmcs(vcpu); + kvm_mmu_print_sptes(vcpu, ve_info->guest_physical_address, "#VE"); + return 1; + } + error_code = 0; if (intr_info & INTR_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); @@ -5371,8 +5388,7 @@ static int handle_io(struct kvm_vcpu *vcpu) return kvm_fast_pio(vcpu, size, port, in); } -static void -vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) +void vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) { /* * Patch in the VMCALL instruction: @@ -5578,7 +5594,7 @@ out: return kvm_complete_insn_gp(vcpu, err); } -static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) +void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { get_debugreg(vcpu->arch.db[0], 0); get_debugreg(vcpu->arch.db[1], 1); @@ -5597,7 +5613,13 @@ static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) set_debugreg(DR6_RESERVED, 6); } -static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) +void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) +{ + lockdep_assert_irqs_disabled(); + set_debugreg(vcpu->arch.dr6, 6); +} + +void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); } @@ -5734,11 +5756,8 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) static int handle_ept_violation(struct kvm_vcpu *vcpu) { - unsigned long exit_qualification; + unsigned long exit_qualification = vmx_get_exit_qual(vcpu); gpa_t gpa; - u64 error_code; - - exit_qualification = vmx_get_exit_qual(vcpu); /* * EPT violation happened while executing iret from NMI, @@ -5754,24 +5773,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); trace_kvm_page_fault(vcpu, gpa, exit_qualification); - /* Is it a read fault? */ - error_code = (exit_qualification & EPT_VIOLATION_ACC_READ) - ? PFERR_USER_MASK : 0; - /* Is it a write fault? */ - error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE) - ? PFERR_WRITE_MASK : 0; - /* Is it a fetch fault? */ - error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR) - ? PFERR_FETCH_MASK : 0; - /* ept page table entry is present? */ - error_code |= (exit_qualification & EPT_VIOLATION_RWX_MASK) - ? PFERR_PRESENT_MASK : 0; - - error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ? - PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; - - vcpu->arch.exit_qualification = exit_qualification; - /* * Check that the GPA doesn't exceed physical memory limits, as that is * a guest page fault. We have to emulate the instruction here, because @@ -5783,7 +5784,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) if (unlikely(allow_smaller_maxphyaddr && !kvm_vcpu_is_legal_gpa(vcpu, gpa))) return kvm_emulate_instruction(vcpu, 0); - return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); + return __vmx_handle_ept_violation(vcpu, gpa, exit_qualification); } static int handle_ept_misconfig(struct kvm_vcpu *vcpu) @@ -5819,11 +5820,35 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu) return 1; } -static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu) +/* + * Returns true if emulation is required (due to the vCPU having invalid state + * with unsrestricted guest mode disabled) and KVM can't faithfully emulate the + * current vCPU state. + */ +static bool vmx_unhandleable_emulation_required(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - return vmx->emulation_required && !vmx->rmode.vm86_active && + if (!vmx->vt.emulation_required) + return false; + + /* + * It is architecturally impossible for emulation to be required when a + * nested VM-Enter is pending completion, as VM-Enter will VM-Fail if + * guest state is invalid and unrestricted guest is disabled, i.e. KVM + * should synthesize VM-Fail instead emulation L2 code. This path is + * only reachable if userspace modifies L2 guest state after KVM has + * performed the nested VM-Enter consistency checks. + */ + if (vmx->nested.nested_run_pending) + return true; + + /* + * KVM only supports emulating exceptions if the vCPU is in Real Mode. + * If emulation is required, KVM can't perform a successful VM-Enter to + * inject the exception. + */ + return !vmx->rmode.vm86_active && (kvm_is_exception_pending(vcpu) || vcpu->arch.exception.injected); } @@ -5836,7 +5861,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) intr_window_requested = exec_controls_get(vmx) & CPU_BASED_INTR_WINDOW_EXITING; - while (vmx->emulation_required && count-- != 0) { + while (vmx->vt.emulation_required && count-- != 0) { if (intr_window_requested && !vmx_interrupt_blocked(vcpu)) return handle_interrupt_window(&vmx->vcpu); @@ -5846,7 +5871,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (!kvm_emulate_instruction(vcpu, 0)) return 0; - if (vmx_emulation_required_with_pending_exception(vcpu)) { + if (vmx_unhandleable_emulation_required(vcpu)) { kvm_prepare_emulation_failure_exit(vcpu); return 0; } @@ -5868,9 +5893,9 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) return 1; } -static int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu) +int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu) { - if (vmx_emulation_required_with_pending_exception(vcpu)) { + if (vmx_unhandleable_emulation_required(vcpu)) { kvm_prepare_emulation_failure_exit(vcpu); return 0; } @@ -5878,38 +5903,6 @@ static int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu) return 1; } -static void grow_ple_window(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned int old = vmx->ple_window; - - vmx->ple_window = __grow_ple_window(old, ple_window, - ple_window_grow, - ple_window_max); - - if (vmx->ple_window != old) { - vmx->ple_window_dirty = true; - trace_kvm_ple_window_update(vcpu->vcpu_id, - vmx->ple_window, old); - } -} - -static void shrink_ple_window(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned int old = vmx->ple_window; - - vmx->ple_window = __shrink_ple_window(old, ple_window, - ple_window_shrink, - ple_window); - - if (vmx->ple_window != old) { - vmx->ple_window_dirty = true; - trace_kvm_ple_window_update(vcpu->vcpu_id, - vmx->ple_window, old); - } -} - /* * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE * exiting, so only get here on cpu with PAUSE-Loop-Exiting. @@ -5945,7 +5938,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) } operand; int gpr_index; - if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_INVPCID)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -6035,7 +6028,7 @@ static int handle_preemption_timer(struct kvm_vcpu *vcpu) /* * When nested=0, all VMX instruction VM Exits filter here. The handlers - * are overwritten by nested_vmx_setup() when nested=1. + * are overwritten by nested_vmx_hardware_setup() when nested=1. */ static int handle_vmx_instruction(struct kvm_vcpu *vcpu) { @@ -6063,7 +6056,7 @@ static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu) * VM-Exits. Unconditionally set the flag here and leave the handling to * vmx_handle_exit(). */ - to_vmx(vcpu)->exit_reason.bus_lock_detected = true; + to_vt(vcpu)->exit_reason.bus_lock_detected = true; return 1; } @@ -6156,15 +6149,14 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { static const int kvm_vmx_max_exit_handlers = ARRAY_SIZE(kvm_vmx_exit_handlers); -static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, - u64 *info1, u64 *info2, - u32 *intr_info, u32 *error_code) +void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); - *reason = vmx->exit_reason.full; + *reason = vmx->vt.exit_reason.full; *info1 = vmx_get_exit_qual(vcpu); - if (!(vmx->exit_reason.failed_vmentry)) { + if (!(vmx->vt.exit_reason.failed_vmentry)) { *info2 = vmx->idt_vectoring_info; *intr_info = vmx_get_intr_info(vcpu); if (is_exception_with_error_code(*intr_info)) @@ -6178,6 +6170,15 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, } } +void vmx_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code) +{ + *intr_info = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD); + if (is_exception_with_error_code(*intr_info)) + *error_code = vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE); + else + *error_code = 0; +} + static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) { if (vmx->pml_pg) { @@ -6189,32 +6190,40 @@ static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + u16 pml_idx, pml_tail_index; u64 *pml_buf; - u16 pml_idx; + int i; pml_idx = vmcs_read16(GUEST_PML_INDEX); /* Do nothing if PML buffer is empty */ - if (pml_idx == (PML_ENTITY_NUM - 1)) + if (pml_idx == PML_HEAD_INDEX) return; + /* + * PML index always points to the next available PML buffer entity + * unless PML log has just overflowed. + */ + pml_tail_index = (pml_idx >= PML_LOG_NR_ENTRIES) ? 0 : pml_idx + 1; - /* PML index always points to next available PML buffer entity */ - if (pml_idx >= PML_ENTITY_NUM) - pml_idx = 0; - else - pml_idx++; - + /* + * PML log is written backwards: the CPU first writes the entry 511 + * then the entry 510, and so on. + * + * Read the entries in the same order they were written, to ensure that + * the dirty ring is filled in the same order the CPU wrote them. + */ pml_buf = page_address(vmx->pml_pg); - for (; pml_idx < PML_ENTITY_NUM; pml_idx++) { + + for (i = PML_HEAD_INDEX; i >= pml_tail_index; i--) { u64 gpa; - gpa = pml_buf[pml_idx]; + gpa = pml_buf[i]; WARN_ON(gpa & (PAGE_SIZE - 1)); kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); } /* reset PML index */ - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX); } static void vmx_dump_sel(char *name, uint32_t sel) @@ -6416,6 +6425,24 @@ void dump_vmcs(struct kvm_vcpu *vcpu) if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID) pr_err("Virtual processor ID = 0x%04x\n", vmcs_read16(VIRTUAL_PROCESSOR_ID)); + if (secondary_exec_control & SECONDARY_EXEC_EPT_VIOLATION_VE) { + struct vmx_ve_information *ve_info = vmx->ve_info; + u64 ve_info_pa = vmcs_read64(VE_INFORMATION_ADDRESS); + + /* + * If KVM is dumping the VMCS, then something has gone wrong + * already. Derefencing an address from the VMCS, which could + * very well be corrupted, is a terrible idea. The virtual + * address is known so use it. + */ + pr_err("VE info address = 0x%016llx%s\n", ve_info_pa, + ve_info_pa == __pa(ve_info) ? "" : "(corrupted!)"); + pr_err("ve_info: 0x%08x 0x%08x 0x%016llx 0x%016llx 0x%016llx 0x%04x\n", + ve_info->exit_reason, ve_info->delivery, + ve_info->exit_qualification, + ve_info->guest_linear_address, + ve_info->guest_physical_address, ve_info->eptp_index); + } } /* @@ -6425,7 +6452,7 @@ void dump_vmcs(struct kvm_vcpu *vcpu) static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); - union vmx_exit_reason exit_reason = vmx->exit_reason; + union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu); u32 vectoring_info = vmx->idt_vectoring_info; u16 exit_handler_index; @@ -6481,7 +6508,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) * the least awful solution for the userspace case without * risking false positives. */ - if (vmx->emulation_required) { + if (vmx->vt.emulation_required) { nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); return 1; } @@ -6491,7 +6518,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) } /* If guest state is invalid, start emulating. L2 is handled above. */ - if (vmx->emulation_required) + if (vmx->vt.emulation_required) return handle_invalid_guest_state(vcpu); if (exit_reason.failed_vmentry) { @@ -6512,33 +6539,15 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 0; } - /* - * Note: - * Do not try to fix EXIT_REASON_EPT_MISCONFIG if it caused by - * delivery event since it indicates guest is accessing MMIO. - * The vm-exit can be triggered again after return to guest that - * will cause infinite loop. - */ if ((vectoring_info & VECTORING_INFO_VALID_MASK) && (exit_reason.basic != EXIT_REASON_EXCEPTION_NMI && exit_reason.basic != EXIT_REASON_EPT_VIOLATION && exit_reason.basic != EXIT_REASON_PML_FULL && exit_reason.basic != EXIT_REASON_APIC_ACCESS && exit_reason.basic != EXIT_REASON_TASK_SWITCH && - exit_reason.basic != EXIT_REASON_NOTIFY)) { - int ndata = 3; - - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; - vcpu->run->internal.data[0] = vectoring_info; - vcpu->run->internal.data[1] = exit_reason.full; - vcpu->run->internal.data[2] = vmx_get_exit_qual(vcpu); - if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { - vcpu->run->internal.data[ndata++] = - vmcs_read64(GUEST_PHYSICAL_ADDRESS); - } - vcpu->run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu; - vcpu->run->internal.ndata = ndata; + exit_reason.basic != EXIT_REASON_NOTIFY && + exit_reason.basic != EXIT_REASON_EPT_MISCONFIG)) { + kvm_prepare_event_vectoring_exit(vcpu, INVALID_GPA); return 0; } @@ -6601,7 +6610,7 @@ unexpected_vmexit: return 0; } -static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) +int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { int ret = __vmx_handle_exit(vcpu, exit_fastpath); @@ -6609,7 +6618,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) * Exit to user space when bus lock detected to inform that there is * a bus lock in guest. */ - if (to_vmx(vcpu)->exit_reason.bus_lock_detected) { + if (vmx_get_exit_reason(vcpu).bus_lock_detected) { if (ret > 0) vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; @@ -6641,9 +6650,10 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) bool flush_l1d; /* - * Clear the per-vcpu flush bit, it gets set again - * either from vcpu_run() or from one of the unsafe - * VMEXIT handlers. + * Clear the per-vcpu flush bit, it gets set again if the vCPU + * is reloaded, i.e. if the vCPU is scheduled out or if KVM + * exits to userspace, or if KVM reaches one of the unsafe + * VMEXIT handlers, e.g. if KVM calls into the emulator. */ flush_l1d = vcpu->arch.l1tf_flush_l1d; vcpu->arch.l1tf_flush_l1d = false; @@ -6662,7 +6672,7 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) vcpu->stat.l1d_flush++; if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) { - native_wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH); + native_wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH); return; } @@ -6689,7 +6699,7 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) : "eax", "ebx", "ecx", "edx"); } -static void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) +void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); int tpr_threshold; @@ -6759,14 +6769,16 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) vmx_update_msr_bitmap_x2apic(vcpu); } -static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) +void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) { const gfn_t gfn = APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT; struct kvm *kvm = vcpu->kvm; struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *slot; + struct page *refcounted_page; unsigned long mmu_seq; kvm_pfn_t pfn; + bool writable; /* Defer reload until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { @@ -6802,37 +6814,58 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) * controls the APIC-access page memslot, and only deletes the memslot * if APICv is permanently inhibited, i.e. the memslot won't reappear. */ - pfn = gfn_to_pfn_memslot(slot, gfn); + pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, &writable, &refcounted_page); if (is_error_noslot_pfn(pfn)) return; read_lock(&vcpu->kvm->mmu_lock); - if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) { + if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - read_unlock(&vcpu->kvm->mmu_lock); - goto out; - } + else + vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(pfn)); - vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(pfn)); - read_unlock(&vcpu->kvm->mmu_lock); + /* + * Do not pin the APIC access page in memory so that it can be freely + * migrated, the MMU notifier will call us again if it is migrated or + * swapped out. KVM backs the memslot with anonymous memory, the pfn + * should always point at a refcounted page (if the pfn is valid). + */ + if (!WARN_ON_ONCE(!refcounted_page)) + kvm_release_page_clean(refcounted_page); /* * No need for a manual TLB flush at this point, KVM has already done a * flush if there were SPTEs pointing at the previous page. */ -out: - /* - * Do not pin apic access page in memory, the MMU notifier - * will call us again if it is migrated or swapped out. - */ - kvm_release_pfn_clean(pfn); + read_unlock(&vcpu->kvm->mmu_lock); } -static void vmx_hwapic_isr_update(int max_isr) +void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) { u16 status; u8 old; + /* + * If L2 is active, defer the SVI update until vmcs01 is loaded, as SVI + * is only relevant for if and only if Virtual Interrupt Delivery is + * enabled in vmcs12, and if VID is enabled then L2 EOIs affect L2's + * vAPIC, not L1's vAPIC. KVM must update vmcs01 on the next nested + * VM-Exit, otherwise L1 with run with a stale SVI. + */ + if (is_guest_mode(vcpu)) { + /* + * KVM is supposed to forward intercepted L2 EOIs to L1 if VID + * is enabled in vmcs12; as above, the EOIs affect L2's vAPIC. + * Note, userspace can stuff state while L2 is active; assert + * that VID is disabled if and only if the vCPU is in KVM_RUN + * to avoid false positives if userspace is setting APIC state. + */ + WARN_ON_ONCE(vcpu->wants_to_run && + nested_cpu_has_vid(get_vmcs12(vcpu))); + to_vmx(vcpu)->nested.update_vmcs01_hwapic_isr = true; + return; + } + if (max_isr == -1) max_isr = 0; @@ -6862,38 +6895,24 @@ static void vmx_set_rvi(int vector) } } -static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) -{ - /* - * When running L2, updating RVI is only relevant when - * vmcs12 virtual-interrupt-delivery enabled. - * However, it can be enabled only when L1 also - * intercepts external-interrupts and in that case - * we should not update vmcs02 RVI but instead intercept - * interrupt. Therefore, do nothing when running L2. - */ - if (!is_guest_mode(vcpu)) - vmx_set_rvi(max_irr); -} - -static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) +int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vcpu_vt *vt = to_vt(vcpu); int max_irr; bool got_posted_interrupt; if (KVM_BUG_ON(!enable_apicv, vcpu->kvm)) return -EIO; - if (pi_test_on(&vmx->pi_desc)) { - pi_clear_on(&vmx->pi_desc); + if (pi_test_on(&vt->pi_desc)) { + pi_clear_on(&vt->pi_desc); /* * IOMMU can write to PID.ON, so the barrier matters even on UP. * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); got_posted_interrupt = - kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr); + kvm_apic_update_irr(vcpu, vt->pi_desc.pir, &max_irr); } else { max_irr = kvm_lapic_find_highest_irr(vcpu); got_posted_interrupt = false; @@ -6922,7 +6941,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) return max_irr; } -static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) return; @@ -6933,14 +6952,6 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } -static void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - pi_clear_on(&vmx->pi_desc); - memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir)); -} - void vmx_do_interrupt_irqoff(unsigned long entry); void vmx_do_nmi_irqoff(void); @@ -6951,37 +6962,34 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) * MSR value is not clobbered by the host activity before the guest * has chance to consume it. * - * Do not blindly read xfd_err here, since this exception might - * be caused by L1 interception on a platform which doesn't - * support xfd at all. + * Update the guest's XFD_ERR if and only if XFD is enabled, as the #NM + * interception may have been caused by L1 interception. Per the SDM, + * XFD_ERR is not modified for non-XFD #NM, i.e. if CR0.TS=1. * - * Do it conditionally upon guest_fpu::xfd. xfd_err matters - * only when xfd contains a non-zero value. - * - * Queuing exception is done in vmx_handle_exit. See comment there. + * Note, XFD_ERR is updated _before_ the #NM interception check, i.e. + * unlike CR2 and DR6, the value is not a payload that is attached to + * the #NM exception. */ - if (vcpu->arch.guest_fpu.fpstate->xfd) - rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); + if (is_xfd_nm_fault(vcpu)) + rdmsrq(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); } -static void handle_exception_irqoff(struct vcpu_vmx *vmx) +static void handle_exception_irqoff(struct kvm_vcpu *vcpu, u32 intr_info) { - u32 intr_info = vmx_get_intr_info(&vmx->vcpu); - /* if exit due to PF check for async PF */ if (is_page_fault(intr_info)) - vmx->vcpu.arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); + vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); /* if exit due to NM, handle before interrupts are enabled */ else if (is_nm_fault(intr_info)) - handle_nm_fault_irqoff(&vmx->vcpu); + handle_nm_fault_irqoff(vcpu); /* Handle machine checks before interrupts are enabled */ else if (is_machine_check(intr_info)) kvm_machine_check(); } -static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) +static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu, + u32 intr_info) { - u32 intr_info = vmx_get_intr_info(vcpu); unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, @@ -6998,24 +7006,22 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) vcpu->arch.at_instruction_boundary = true; } -static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) +void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (vmx->emulation_required) + if (to_vt(vcpu)->emulation_required) return; - if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) - handle_external_interrupt_irqoff(vcpu); - else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI) - handle_exception_irqoff(vmx); + if (vmx_get_exit_reason(vcpu).basic == EXIT_REASON_EXTERNAL_INTERRUPT) + handle_external_interrupt_irqoff(vcpu, vmx_get_intr_info(vcpu)); + else if (vmx_get_exit_reason(vcpu).basic == EXIT_REASON_EXCEPTION_NMI) + handle_exception_irqoff(vcpu, vmx_get_intr_info(vcpu)); } /* * The kvm parameter can be NULL (module initialization, or invocation before * VM creation). Be sure to check the kvm parameter before using it. */ -static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) +bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_SMBASE: @@ -7113,13 +7119,17 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, case INTR_TYPE_SOFT_EXCEPTION: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); fallthrough; - case INTR_TYPE_HARD_EXCEPTION: - if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { - u32 err = vmcs_read32(error_code_field); - kvm_requeue_exception_e(vcpu, vector, err); - } else - kvm_requeue_exception(vcpu, vector); + case INTR_TYPE_HARD_EXCEPTION: { + u32 error_code = 0; + + if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) + error_code = vmcs_read32(error_code_field); + + kvm_requeue_exception(vcpu, vector, + idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK, + error_code); break; + } case INTR_TYPE_SOFT_INTR: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); fallthrough; @@ -7138,7 +7148,7 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx) IDT_VECTORING_ERROR_CODE); } -static void vmx_cancel_injection(struct kvm_vcpu *vcpu) +void vmx_cancel_injection(struct kvm_vcpu *vcpu) { __vmx_complete_interrupts(vcpu, vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), @@ -7214,7 +7224,7 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, return; if (flags & VMX_RUN_SAVE_SPEC_CTRL) - vmx->spec_ctrl = __rdmsr(MSR_IA32_SPEC_CTRL); + vmx->spec_ctrl = native_rdmsrq(MSR_IA32_SPEC_CTRL); /* * If the guest/host SPEC_CTRL values differ, restore the host value. @@ -7225,7 +7235,7 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, */ if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) || vmx->spec_ctrl != hostval) - native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval); + native_wrmsrq(MSR_IA32_SPEC_CTRL, hostval); barrier_nospec(); } @@ -7238,19 +7248,35 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu, * the fastpath even, all other exits must use the slow path. */ if (is_guest_mode(vcpu) && - to_vmx(vcpu)->exit_reason.basic != EXIT_REASON_PREEMPTION_TIMER) + vmx_get_exit_reason(vcpu).basic != EXIT_REASON_PREEMPTION_TIMER) return EXIT_FASTPATH_NONE; - switch (to_vmx(vcpu)->exit_reason.basic) { + switch (vmx_get_exit_reason(vcpu).basic) { case EXIT_REASON_MSR_WRITE: return handle_fastpath_set_msr_irqoff(vcpu); case EXIT_REASON_PREEMPTION_TIMER: return handle_fastpath_preemption_timer(vcpu, force_immediate_exit); + case EXIT_REASON_HLT: + return handle_fastpath_hlt(vcpu); default: return EXIT_FASTPATH_NONE; } } +noinstr void vmx_handle_nmi(struct kvm_vcpu *vcpu) +{ + if ((u16)vmx_get_exit_reason(vcpu).basic != EXIT_REASON_EXCEPTION_NMI || + !is_nmi(vmx_get_intr_info(vcpu))) + return; + + kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + fred_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR); + else + vmx_do_nmi_irqoff(); + kvm_after_interrupt(vcpu); +} + static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, unsigned int flags) { @@ -7263,10 +7289,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, * mitigation for MDS is done late in VMentry and is still * executed in spite of L1D Flush. This is because an extra VERW * should not matter much after the big hammer L1D Flush. + * + * cpu_buf_vm_clear is used when system is not vulnerable to MDS/TAA, + * and is affected by MMIO Stale Data. In such cases mitigation in only + * needed against an MMIO capable guest. */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mmio_stale_data_clear) && + else if (static_branch_unlikely(&cpu_buf_vm_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers(); @@ -7286,29 +7316,21 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vmx_enable_fb_clear(vmx); if (unlikely(vmx->fail)) { - vmx->exit_reason.full = 0xdead; + vmx->vt.exit_reason.full = 0xdead; goto out; } - vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); - if (likely(!vmx->exit_reason.failed_vmentry)) + vmx->vt.exit_reason.full = vmcs_read32(VM_EXIT_REASON); + if (likely(!vmx_get_exit_reason(vcpu).failed_vmentry)) vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI && - is_nmi(vmx_get_intr_info(vcpu))) { - kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); - if (cpu_feature_enabled(X86_FEATURE_FRED)) - fred_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR); - else - vmx_do_nmi_irqoff(); - kvm_after_interrupt(vcpu); - } + vmx_handle_nmi(vcpu); out: guest_state_exit_irqoff(); } -static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; @@ -7323,15 +7345,15 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) * start emulation until we arrive back to a valid state. Synthesize a * consistency check VM-Exit due to invalid guest state and bail. */ - if (unlikely(vmx->emulation_required)) { + if (unlikely(vmx->vt.emulation_required)) { vmx->fail = 0; - vmx->exit_reason.full = EXIT_REASON_INVALID_STATE; - vmx->exit_reason.failed_vmentry = 1; + vmx->vt.exit_reason.full = EXIT_REASON_INVALID_STATE; + vmx->vt.exit_reason.failed_vmentry = 1; kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1); - vmx->exit_qualification = ENTRY_FAIL_DEFAULT; + vmx->vt.exit_qualification = ENTRY_FAIL_DEFAULT; kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2); - vmx->exit_intr_info = 0; + vmx->vt.exit_intr_info = 0; return EXIT_FASTPATH_NONE; } @@ -7373,10 +7395,6 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) vmx->loaded_vmcs->host_state.cr4 = cr4; } - /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ - if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) - set_debugreg(vcpu->arch.dr6, 6); - /* When single-stepping over STI and MOV SS, we must clear the * corresponding interruptibility bits in the guest state. Otherwise * vmentry fails as it then expects bit 14 (BS) in pending debug @@ -7412,8 +7430,8 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) } /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ - if (vmx->host_debugctlmsr) - update_debugctlmsr(vmx->host_debugctlmsr); + if (vcpu->arch.host_debugctl) + update_debugctlmsr(vcpu->arch.host_debugctl); #ifndef CONFIG_X86_64 /* @@ -7438,7 +7456,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) * checking. */ if (vmx->nested.nested_run_pending && - !vmx->exit_reason.failed_vmentry) + !vmx_get_exit_reason(vcpu).failed_vmentry) ++vcpu->stat.nested_run; vmx->nested.nested_run_pending = 0; @@ -7447,12 +7465,12 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) if (unlikely(vmx->fail)) return EXIT_FASTPATH_NONE; - if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY)) + if (unlikely((u16)vmx_get_exit_reason(vcpu).basic == EXIT_REASON_MCE_DURING_VMENTRY)) kvm_machine_check(); trace_kvm_exit(vcpu, KVM_ISA_VMX); - if (unlikely(vmx->exit_reason.failed_vmentry)) + if (unlikely(vmx_get_exit_reason(vcpu).failed_vmentry)) return EXIT_FASTPATH_NONE; vmx->loaded_vmcs->launched = 1; @@ -7463,7 +7481,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) return vmx_exit_handlers_fastpath(vcpu, force_immediate_exit); } -static void vmx_vcpu_free(struct kvm_vcpu *vcpu) +void vmx_vcpu_free(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7472,9 +7490,10 @@ static void vmx_vcpu_free(struct kvm_vcpu *vcpu) free_vpid(vmx->vpid); nested_vmx_free_vcpu(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); + free_page((unsigned long)vmx->ve_info); } -static int vmx_vcpu_create(struct kvm_vcpu *vcpu) +int vmx_vcpu_create(struct kvm_vcpu *vcpu) { struct vmx_uret_msr *tsx_ctrl; struct vcpu_vmx *vmx; @@ -7483,7 +7502,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0); vmx = to_vmx(vcpu); - INIT_LIST_HEAD(&vmx->pi_wakeup_list); + INIT_LIST_HEAD(&vmx->vt.pi_wakeup_list); err = -ENOMEM; @@ -7565,9 +7584,23 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) goto free_vmcs; } + err = -ENOMEM; + if (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_EPT_VIOLATION_VE) { + struct page *page; + + BUILD_BUG_ON(sizeof(*vmx->ve_info) > PAGE_SIZE); + + /* ve_info must be page aligned. */ + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!page) + goto free_vmcs; + + vmx->ve_info = page_to_virt(page); + } + if (vmx_can_use_ipiv(vcpu)) WRITE_ONCE(to_kvm_vmx(vcpu->kvm)->pid_table[vcpu->vcpu_id], - __pa(&vmx->pi_desc) | PID_TABLE_ENTRY_VALID); + __pa(&vmx->vt.pi_desc) | PID_TABLE_ENTRY_VALID); return 0; @@ -7583,7 +7616,7 @@ free_vpid: #define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" #define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" -static int vmx_vm_init(struct kvm *kvm) +int vmx_vm_init(struct kvm *kvm) { if (!ple_gap) kvm->arch.pause_in_guest = true; @@ -7594,6 +7627,7 @@ static int vmx_vm_init(struct kvm *kvm) case L1TF_MITIGATION_FLUSH_NOWARN: /* 'I explicitly don't care' is set */ break; + case L1TF_MITIGATION_AUTO: case L1TF_MITIGATION_FLUSH: case L1TF_MITIGATION_FLUSH_NOSMT: case L1TF_MITIGATION_FULL: @@ -7611,44 +7645,37 @@ static int vmx_vm_init(struct kvm *kvm) break; } } + + if (enable_pml) + kvm->arch.cpu_dirty_log_size = PML_LOG_NR_ENTRIES; return 0; } -static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +static inline bool vmx_ignore_guest_pat(struct kvm *kvm) { - /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in - * memory aliases with conflicting memory types and sometimes MCEs. - * We have to be careful as to what are honored and when. - * - * For MMIO, guest CD/MTRR are ignored. The EPT memory type is set to - * UC. The effective memory type is UC or WC depending on guest PAT. - * This was historically the source of MCEs and we want to be - * conservative. - * - * When there is no need to deal with noncoherent DMA (e.g., no VT-d - * or VT-d has snoop control), guest CD/MTRR/PAT are all ignored. The - * EPT memory type is set to WB. The effective memory type is forced - * WB. - * - * Otherwise, we trust guest. Guest CD/MTRR/PAT are all honored. The - * EPT memory type is used to emulate guest CD/MTRR. + /* + * Non-coherent DMA devices need the guest to flush CPU properly. + * In that case it is not possible to map all guest RAM as WB, so + * always trust guest PAT. */ + return !kvm_arch_has_noncoherent_dma(kvm) && + kvm_check_has_quirk(kvm, KVM_X86_QUIRK_IGNORE_GUEST_PAT); +} +u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +{ + /* + * Force UC for host MMIO regions, as allowing the guest to access MMIO + * with cacheable accesses will result in Machine Checks. + */ if (is_mmio) return MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) + /* Force WB if ignoring guest PAT */ + if (vmx_ignore_guest_pat(vcpu->kvm)) return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; - if (kvm_read_cr0_bits(vcpu, X86_CR0_CD)) { - if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - return MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT; - else - return (MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT) | - VMX_EPT_IPAT_BIT; - } - - return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; + return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT); } static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl) @@ -7786,7 +7813,7 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4)); } -static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) +void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7795,12 +7822,8 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) * to the guest. XSAVES depends on CR4.OSXSAVE, and CR4.OSXSAVE can be * set if and only if XSAVE is supported. */ - if (boot_cpu_has(X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVE)) - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_XSAVES); - - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VMX); - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LAM); + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVE)) + guest_cpu_cap_clear(vcpu, X86_FEATURE_XSAVES); vmx_setup_uret_msrs(vmx); @@ -7808,7 +7831,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmcs_set_secondary_exec_control(vmx, vmx_secondary_exec_control(vmx)); - if (guest_can_use(vcpu, X86_FEATURE_VMX)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; @@ -7817,25 +7840,25 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) ~(FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX); - if (guest_can_use(vcpu, X86_FEATURE_VMX)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) nested_vmx_cr_fixed1_bits_update(vcpu); if (boot_cpu_has(X86_FEATURE_INTEL_PT) && - guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT)) + guest_cpu_cap_has(vcpu, X86_FEATURE_INTEL_PT)) update_intel_pt_cfg(vcpu); if (boot_cpu_has(X86_FEATURE_RTM)) { struct vmx_uret_msr *msr; msr = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (msr) { - bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM); + bool enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_RTM); vmx_set_guest_uret_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE); } } if (kvm_cpu_cap_has(X86_FEATURE_XFD)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)); + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)); if (boot_cpu_has(X86_FEATURE_IBPB)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W, @@ -7843,17 +7866,17 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) if (boot_cpu_has(X86_FEATURE_FLUSH_L1D)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W, - !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); + !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); set_cr4_guest_host_mask(vmx); vmx_write_encls_bitmap(vcpu, NULL); - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX)) + if (guest_cpu_cap_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)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_SGX_LC_ENABLED; else @@ -7873,7 +7896,7 @@ static __init u64 vmx_get_perf_capabilities(void) return 0; if (boot_cpu_has(X86_FEATURE_PDCM)) - rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); + rdmsrq(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) { x86_perf_get_lbr(&vmx_lbr_caps); @@ -7947,6 +7970,7 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_clear(X86_FEATURE_SGX_LC); kvm_cpu_cap_clear(X86_FEATURE_SGX1); kvm_cpu_cap_clear(X86_FEATURE_SGX2); + kvm_cpu_cap_clear(X86_FEATURE_SGX_EDECCSSA); } if (vmx_umip_emulated()) @@ -7967,66 +7991,86 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); } -static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, - struct x86_instruction_info *info) +static bool vmx_is_io_intercepted(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + unsigned long *exit_qualification) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned short port; - bool intercept; int size; + bool imm; + + /* + * If the 'use IO bitmaps' VM-execution control is 0, IO instruction + * VM-exits depend on the 'unconditional IO exiting' VM-execution + * control. + * + * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. + */ + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); if (info->intercept == x86_intercept_in || info->intercept == x86_intercept_ins) { port = info->src_val; size = info->dst_bytes; + imm = info->src_type == OP_IMM; } else { port = info->dst_val; size = info->src_bytes; + imm = info->dst_type == OP_IMM; } - /* - * If the 'use IO bitmaps' VM-execution control is 0, IO instruction - * VM-exits depend on the 'unconditional IO exiting' VM-execution - * control. - * - * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. - */ - if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) - intercept = nested_cpu_has(vmcs12, - CPU_BASED_UNCOND_IO_EXITING); - else - intercept = nested_vmx_check_io_bitmaps(vcpu, port, size); - /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ - return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; + *exit_qualification = ((unsigned long)port << 16) | (size - 1); + + if (info->intercept == x86_intercept_ins || + info->intercept == x86_intercept_outs) + *exit_qualification |= BIT(4); + + if (info->rep_prefix) + *exit_qualification |= BIT(5); + + if (imm) + *exit_qualification |= BIT(6); + + return nested_vmx_check_io_bitmaps(vcpu, port, size); } -static int vmx_check_intercept(struct kvm_vcpu *vcpu, - struct x86_instruction_info *info, - enum x86_intercept_stage stage, - struct x86_exception *exception) +int vmx_check_intercept(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage, + struct x86_exception *exception) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned long exit_qualification = 0; + u32 vm_exit_reason; + u64 exit_insn_len; switch (info->intercept) { - /* - * 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_rdpid: + /* + * RDPID causes #UD if not enabled through secondary execution + * controls (ENABLE_RDTSCP). Note, the implicit MSR access to + * TSC_AUX is NOT subject to interception, i.e. checking only + * the dedicated execution control is architecturally correct. + */ if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_RDTSCP)) { exception->vector = UD_VECTOR; exception->error_code_valid = false; return X86EMUL_PROPAGATE_FAULT; } - break; + return X86EMUL_CONTINUE; case x86_intercept_in: case x86_intercept_ins: case x86_intercept_out: case x86_intercept_outs: - return vmx_check_intercept_io(vcpu, info); + if (!vmx_is_io_intercepted(vcpu, info, &exit_qualification)) + return X86EMUL_CONTINUE; + + vm_exit_reason = EXIT_REASON_IO_INSTRUCTION; + break; case x86_intercept_lgdt: case x86_intercept_lidt: @@ -8039,7 +8083,24 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC)) return X86EMUL_CONTINUE; - /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + if (info->intercept == x86_intercept_lldt || + info->intercept == x86_intercept_ltr || + info->intercept == x86_intercept_sldt || + info->intercept == x86_intercept_str) + vm_exit_reason = EXIT_REASON_LDTR_TR; + else + vm_exit_reason = EXIT_REASON_GDTR_IDTR; + /* + * FIXME: Decode the ModR/M to generate the correct exit + * qualification for memory operands. + */ + break; + + case x86_intercept_hlt: + if (!nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING)) + return X86EMUL_CONTINUE; + + vm_exit_reason = EXIT_REASON_HLT; break; case x86_intercept_pause: @@ -8052,17 +8113,24 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, * the PAUSE. */ if ((info->rep_prefix != REPE_PREFIX) || - !nested_cpu_has2(vmcs12, CPU_BASED_PAUSE_EXITING)) + !nested_cpu_has(vmcs12, CPU_BASED_PAUSE_EXITING)) return X86EMUL_CONTINUE; + vm_exit_reason = EXIT_REASON_PAUSE_INSTRUCTION; break; /* TODO: check more intercepts... */ default: - break; + return X86EMUL_UNHANDLEABLE; } - return X86EMUL_UNHANDLEABLE; + exit_insn_len = abs_diff((s64)info->next_rip, (s64)info->rip); + if (!exit_insn_len || exit_insn_len > X86_MAX_INSTRUCTION_LENGTH) + return X86EMUL_UNHANDLEABLE; + + __nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification, + exit_insn_len); + return X86EMUL_INTERCEPTED; } #ifdef CONFIG_X86_64 @@ -8084,8 +8152,8 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift, return 0; } -static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, - bool *expired) +int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, + bool *expired) { struct vcpu_vmx *vmx; u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; @@ -8124,18 +8192,12 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, return 0; } -static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) +void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) { to_vmx(vcpu)->hv_deadline_tsc = -1; } #endif -static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) -{ - if (!kvm_pause_in_guest(vcpu->kvm)) - shrink_ple_window(vcpu); -} - void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -8159,7 +8221,7 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML); } -static void vmx_setup_mce(struct kvm_vcpu *vcpu) +void vmx_setup_mce(struct kvm_vcpu *vcpu) { if (vcpu->arch.mcg_cap & MCG_LMCE_P) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= @@ -8170,7 +8232,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) } #ifdef CONFIG_KVM_SMM -static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { /* we need a nested vmexit to enter SMM, postpone if run is pending */ if (to_vmx(vcpu)->nested.nested_run_pending) @@ -8178,7 +8240,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !is_smm(vcpu); } -static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) +int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -8199,7 +8261,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) return 0; } -static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) +int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; @@ -8220,18 +8282,18 @@ static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) return 0; } -static void vmx_enable_smi_window(struct kvm_vcpu *vcpu) +void vmx_enable_smi_window(struct kvm_vcpu *vcpu) { /* RSM will cause a vmexit anyway. */ } #endif -static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) +bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { return to_vmx(vcpu)->nested.vmxon && !is_guest_mode(vcpu); } -static void vmx_migrate_timers(struct kvm_vcpu *vcpu) +void vmx_migrate_timers(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { struct hrtimer *timer = &to_vmx(vcpu)->nested.preemption_timer; @@ -8241,7 +8303,7 @@ static void vmx_migrate_timers(struct kvm_vcpu *vcpu) } } -static void vmx_hardware_unsetup(void) +void vmx_hardware_unsetup(void) { kvm_set_posted_intr_wakeup_handler(NULL); @@ -8251,18 +8313,7 @@ static void vmx_hardware_unsetup(void) free_kvm_area(); } -#define VMX_REQUIRED_APICV_INHIBITS \ -( \ - BIT(APICV_INHIBIT_REASON_DISABLE)| \ - BIT(APICV_INHIBIT_REASON_ABSENT) | \ - BIT(APICV_INHIBIT_REASON_HYPERV) | \ - BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ - BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ - BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ - BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) \ -) - -static void vmx_vm_destroy(struct kvm *kvm) +void vmx_vm_destroy(struct kvm *kvm) { struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); @@ -8313,148 +8364,6 @@ gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags return (sign_extend64(gva, lam_bit) & ~BIT_ULL(63)) | (gva & BIT_ULL(63)); } -static struct kvm_x86_ops vmx_x86_ops __initdata = { - .name = KBUILD_MODNAME, - - .check_processor_compatibility = vmx_check_processor_compat, - - .hardware_unsetup = vmx_hardware_unsetup, - - .hardware_enable = vmx_hardware_enable, - .hardware_disable = vmx_hardware_disable, - .has_emulated_msr = vmx_has_emulated_msr, - - .vm_size = sizeof(struct kvm_vmx), - .vm_init = vmx_vm_init, - .vm_destroy = vmx_vm_destroy, - - .vcpu_precreate = vmx_vcpu_precreate, - .vcpu_create = vmx_vcpu_create, - .vcpu_free = vmx_vcpu_free, - .vcpu_reset = vmx_vcpu_reset, - - .prepare_switch_to_guest = vmx_prepare_switch_to_guest, - .vcpu_load = vmx_vcpu_load, - .vcpu_put = vmx_vcpu_put, - - .update_exception_bitmap = vmx_update_exception_bitmap, - .get_msr_feature = vmx_get_msr_feature, - .get_msr = vmx_get_msr, - .set_msr = vmx_set_msr, - .get_segment_base = vmx_get_segment_base, - .get_segment = vmx_get_segment, - .set_segment = vmx_set_segment, - .get_cpl = vmx_get_cpl, - .get_cs_db_l_bits = vmx_get_cs_db_l_bits, - .is_valid_cr0 = vmx_is_valid_cr0, - .set_cr0 = vmx_set_cr0, - .is_valid_cr4 = vmx_is_valid_cr4, - .set_cr4 = vmx_set_cr4, - .set_efer = vmx_set_efer, - .get_idt = vmx_get_idt, - .set_idt = vmx_set_idt, - .get_gdt = vmx_get_gdt, - .set_gdt = vmx_set_gdt, - .set_dr7 = vmx_set_dr7, - .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, - .cache_reg = vmx_cache_reg, - .get_rflags = vmx_get_rflags, - .set_rflags = vmx_set_rflags, - .get_if_flag = vmx_get_if_flag, - - .flush_tlb_all = vmx_flush_tlb_all, - .flush_tlb_current = vmx_flush_tlb_current, - .flush_tlb_gva = vmx_flush_tlb_gva, - .flush_tlb_guest = vmx_flush_tlb_guest, - - .vcpu_pre_run = vmx_vcpu_pre_run, - .vcpu_run = vmx_vcpu_run, - .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = vmx_skip_emulated_instruction, - .update_emulated_instruction = vmx_update_emulated_instruction, - .set_interrupt_shadow = vmx_set_interrupt_shadow, - .get_interrupt_shadow = vmx_get_interrupt_shadow, - .patch_hypercall = vmx_patch_hypercall, - .inject_irq = vmx_inject_irq, - .inject_nmi = vmx_inject_nmi, - .inject_exception = vmx_inject_exception, - .cancel_injection = vmx_cancel_injection, - .interrupt_allowed = vmx_interrupt_allowed, - .nmi_allowed = vmx_nmi_allowed, - .get_nmi_mask = vmx_get_nmi_mask, - .set_nmi_mask = vmx_set_nmi_mask, - .enable_nmi_window = vmx_enable_nmi_window, - .enable_irq_window = vmx_enable_irq_window, - .update_cr8_intercept = vmx_update_cr8_intercept, - .set_virtual_apic_mode = vmx_set_virtual_apic_mode, - .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, - .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_pre_state_restore = vmx_apicv_pre_state_restore, - .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, - .hwapic_irr_update = vmx_hwapic_irr_update, - .hwapic_isr_update = vmx_hwapic_isr_update, - .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, - .sync_pir_to_irr = vmx_sync_pir_to_irr, - .deliver_interrupt = vmx_deliver_interrupt, - .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt, - - .set_tss_addr = vmx_set_tss_addr, - .set_identity_map_addr = vmx_set_identity_map_addr, - .get_mt_mask = vmx_get_mt_mask, - - .get_exit_info = vmx_get_exit_info, - - .vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid, - - .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - - .get_l2_tsc_offset = vmx_get_l2_tsc_offset, - .get_l2_tsc_multiplier = vmx_get_l2_tsc_multiplier, - .write_tsc_offset = vmx_write_tsc_offset, - .write_tsc_multiplier = vmx_write_tsc_multiplier, - - .load_mmu_pgd = vmx_load_mmu_pgd, - - .check_intercept = vmx_check_intercept, - .handle_exit_irqoff = vmx_handle_exit_irqoff, - - .sched_in = vmx_sched_in, - - .cpu_dirty_log_size = PML_ENTITY_NUM, - .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging, - - .nested_ops = &vmx_nested_ops, - - .pi_update_irte = vmx_pi_update_irte, - .pi_start_assignment = vmx_pi_start_assignment, - -#ifdef CONFIG_X86_64 - .set_hv_timer = vmx_set_hv_timer, - .cancel_hv_timer = vmx_cancel_hv_timer, -#endif - - .setup_mce = vmx_setup_mce, - -#ifdef CONFIG_KVM_SMM - .smi_allowed = vmx_smi_allowed, - .enter_smm = vmx_enter_smm, - .leave_smm = vmx_leave_smm, - .enable_smi_window = vmx_enable_smi_window, -#endif - - .check_emulate_instruction = vmx_check_emulate_instruction, - .apic_init_signal_blocked = vmx_apic_init_signal_blocked, - .migrate_timers = vmx_migrate_timers, - - .msr_filter_changed = vmx_msr_filter_changed, - .complete_emulated_msr = kvm_complete_insn_gp, - - .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, - - .get_untagged_addr = vmx_get_untagged_addr, -}; - static unsigned int vmx_handle_intel_pt_intr(void) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); @@ -8500,18 +8409,16 @@ static void __init vmx_setup_me_spte_mask(void) u64 me_mask = 0; /* - * kvm_get_shadow_phys_bits() returns shadow_phys_bits. Use - * the former to avoid exposing shadow_phys_bits. - * * On pre-MKTME system, boot_cpu_data.x86_phys_bits equals to - * shadow_phys_bits. On MKTME and/or TDX capable systems, + * kvm_host.maxphyaddr. On MKTME and/or TDX capable systems, * boot_cpu_data.x86_phys_bits holds the actual physical address - * w/o the KeyID bits, and shadow_phys_bits equals to MAXPHYADDR - * reported by CPUID. Those bits between are KeyID bits. + * w/o the KeyID bits, and kvm_host.maxphyaddr equals to + * MAXPHYADDR reported by CPUID. Those bits between are KeyID bits. */ - if (boot_cpu_data.x86_phys_bits != kvm_get_shadow_phys_bits()) + if (boot_cpu_data.x86_phys_bits != kvm_host.maxphyaddr) me_mask = rsvd_bits(boot_cpu_data.x86_phys_bits, - kvm_get_shadow_phys_bits() - 1); + kvm_host.maxphyaddr - 1); + /* * Unlike SME, host kernel doesn't support setting up any * MKTME KeyID on Intel platforms. No memory encryption @@ -8520,9 +8427,7 @@ static void __init vmx_setup_me_spte_mask(void) kvm_mmu_set_me_spte_mask(0, me_mask); } -static struct kvm_x86_init_ops vmx_init_ops __initdata; - -static __init int hardware_setup(void) +__init int vmx_hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; @@ -8536,15 +8441,11 @@ static __init int hardware_setup(void) if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) return -EIO; - if (cpu_has_perf_global_ctrl_bug()) - pr_warn_once("VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " - "does not work properly. Using workaround\n"); - if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); if (boot_cpu_has(X86_FEATURE_MPX)) { - rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs); + rdmsrq(MSR_IA32_BNDCFGS, host_bndcfgs); WARN_ONCE(host_bndcfgs, "BNDCFGS in host will be lost"); } @@ -8591,16 +8492,16 @@ static __init int hardware_setup(void) * using the APIC_ACCESS_ADDR VMCS field. */ if (!flexpriority_enabled) - vmx_x86_ops.set_apic_access_page_addr = NULL; + vt_x86_ops.set_apic_access_page_addr = NULL; if (!cpu_has_vmx_tpr_shadow()) - vmx_x86_ops.update_cr8_intercept = NULL; + vt_x86_ops.update_cr8_intercept = NULL; #if IS_ENABLED(CONFIG_HYPERV) if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH && enable_ept) { - vmx_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; - vmx_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; + vt_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; + vt_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; } #endif @@ -8615,7 +8516,7 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_apicv()) enable_apicv = 0; if (!enable_apicv) - vmx_x86_ops.sync_pir_to_irr = NULL; + vt_x86_ops.sync_pir_to_irr = NULL; if (!enable_apicv || !cpu_has_vmx_ipiv()) enable_ipiv = false; @@ -8633,6 +8534,8 @@ static __init int hardware_setup(void) if (enable_ept) kvm_mmu_set_ept_masks(enable_ept_ad_bits, cpu_has_vmx_ept_execute_only()); + else + vt_x86_ops.get_mt_mask = NULL; /* * Setup shadow_me_value/shadow_me_mask to include MKTME KeyID @@ -8650,9 +8553,6 @@ static __init int hardware_setup(void) if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml()) enable_pml = 0; - if (!enable_pml) - vmx_x86_ops.cpu_dirty_log_size = 0; - if (!cpu_has_vmx_preemption_timer()) enable_preemption_timer = false; @@ -8660,7 +8560,7 @@ static __init int hardware_setup(void) u64 use_timer_freq = 5000ULL * 1000 * 1000; cpu_preemption_timer_multi = - vmcs_config.misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; + vmx_misc_preemption_timer_rate(vmcs_config.misc); if (tsc_khz) use_timer_freq = (u64)tsc_khz * 1000; @@ -8676,8 +8576,8 @@ static __init int hardware_setup(void) } if (!enable_preemption_timer) { - vmx_x86_ops.set_hv_timer = NULL; - vmx_x86_ops.cancel_hv_timer = NULL; + vt_x86_ops.set_hv_timer = NULL; + vt_x86_ops.cancel_hv_timer = NULL; } kvm_caps.supported_mce_cap |= MCG_LMCE_P; @@ -8688,9 +8588,9 @@ static __init int hardware_setup(void) if (!enable_ept || !enable_pmu || !cpu_has_vmx_intel_pt()) pt_mode = PT_MODE_SYSTEM; if (pt_mode == PT_MODE_HOST_GUEST) - vmx_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr; + vt_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr; else - vmx_init_ops.handle_intel_pt_intr = NULL; + vt_init_ops.handle_intel_pt_intr = NULL; setup_default_sgx_lepubkeyhash(); @@ -8710,17 +8610,30 @@ static __init int hardware_setup(void) kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler); + /* + * On Intel CPUs that lack self-snoop feature, letting the guest control + * memory types may result in unexpected behavior. So always ignore guest + * PAT on those CPUs and map VM as writeback, not allowing userspace to + * disable the quirk. + * + * On certain Intel CPUs (e.g. SPR, ICX), though self-snoop feature is + * supported, UC is slow enough to cause issues with some older guests (e.g. + * an old version of bochs driver uses ioremap() instead of ioremap_wc() to + * map the video RAM, causing wayland desktop to fail to get started + * correctly). To avoid breaking those older guests that rely on KVM to force + * memory type to WB, provide KVM_X86_QUIRK_IGNORE_GUEST_PAT to preserve the + * safer (for performance) default behavior. + * + * On top of this, non-coherent DMA devices need the guest to flush CPU + * caches properly. This also requires honoring guest PAT, and is forced + * independent of the quirk in vmx_ignore_guest_pat(). + */ + if (!static_cpu_has(X86_FEATURE_SELFSNOOP)) + kvm_caps.supported_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT; + kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT; return r; } -static struct kvm_x86_init_ops vmx_init_ops __initdata = { - .hardware_setup = hardware_setup, - .handle_intel_pt_intr = NULL, - - .runtime_ops = &vmx_x86_ops, - .pmu_ops = &intel_pmu_ops, -}; - static void vmx_cleanup_l1d_flush(void) { if (vmx_l1d_flush_pages) { @@ -8731,25 +8644,16 @@ static void vmx_cleanup_l1d_flush(void) l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; } -static void __vmx_exit(void) +void vmx_exit(void) { allow_smaller_maxphyaddr = false; - cpu_emergency_unregister_virt_callback(vmx_emergency_disable); - vmx_cleanup_l1d_flush(); -} -static void vmx_exit(void) -{ - kvm_exit(); kvm_x86_vendor_exit(); - - __vmx_exit(); } -module_exit(vmx_exit); -static int __init vmx_init(void) +int __init vmx_init(void) { int r, cpu; @@ -8762,7 +8666,7 @@ static int __init vmx_init(void) */ hv_init_evmcs(); - r = kvm_x86_vendor_init(&vmx_init_ops); + r = kvm_x86_vendor_init(&vt_init_ops); if (r) return r; @@ -8783,8 +8687,6 @@ static int __init vmx_init(void) pi_init_cpu(cpu); } - cpu_emergency_register_virt_callback(vmx_emergency_disable); - vmx_check_vmcs12_offsets(); /* @@ -8795,21 +8697,9 @@ static int __init vmx_init(void) if (!enable_ept) allow_smaller_maxphyaddr = true; - /* - * Common KVM initialization _must_ come last, after this, /dev/kvm is - * exposed to userspace! - */ - r = kvm_init(sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx), - THIS_MODULE); - if (r) - goto err_kvm_init; - return 0; -err_kvm_init: - __vmx_exit(); err_l1d_flush: kvm_x86_vendor_exit(); return r; } -module_init(vmx_init); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 90f9e4434646..6d1e40ecc024 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -7,19 +7,17 @@ #include <asm/kvm.h> #include <asm/intel_pt.h> #include <asm/perf_event.h> +#include <asm/posted_intr.h> #include "capabilities.h" #include "../kvm_cache_regs.h" -#include "posted_intr.h" +#include "pmu_intel.h" #include "vmcs.h" #include "vmx_ops.h" #include "../cpuid.h" #include "run_flags.h" #include "../mmu.h" - -#define MSR_TYPE_R 1 -#define MSR_TYPE_W 2 -#define MSR_TYPE_RW 3 +#include "common.h" #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) @@ -71,47 +69,6 @@ struct pt_desc { struct pt_ctx guest; }; -union vmx_exit_reason { - struct { - u32 basic : 16; - u32 reserved16 : 1; - u32 reserved17 : 1; - u32 reserved18 : 1; - u32 reserved19 : 1; - u32 reserved20 : 1; - u32 reserved21 : 1; - u32 reserved22 : 1; - u32 reserved23 : 1; - u32 reserved24 : 1; - u32 reserved25 : 1; - u32 bus_lock_detected : 1; - u32 enclave_mode : 1; - u32 smi_pending_mtf : 1; - u32 smi_from_vmx_root : 1; - u32 reserved30 : 1; - u32 failed_vmentry : 1; - }; - u32 full; -}; - -struct lbr_desc { - /* Basic info about guest LBR records. */ - struct x86_pmu_lbr records; - - /* - * Emulate LBR feature via passthrough LBR registers when the - * per-vcpu guest LBR event is scheduled on the current pcpu. - * - * The records may be inaccurate if the host reclaims the LBR. - */ - struct perf_event *event; - - /* True if LBRs are marked as not intercepted in the MSR bitmap */ - bool msr_passthrough; -}; - -extern struct x86_pmu_lbr vmx_lbr_caps; - /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -180,6 +137,7 @@ struct nested_vmx { bool reload_vmcs01_apic_access_page; bool update_vmcs01_cpu_dirty_logging; bool update_vmcs01_apicv_status; + bool update_vmcs01_hwapic_isr; /* * Enlightened VMCS has been enabled. It does not mean that L1 has to @@ -204,8 +162,6 @@ struct nested_vmx { struct kvm_host_map virtual_apic_map; struct kvm_host_map pi_desc_map; - struct kvm_host_map msr_bitmap_map; - struct pi_desc *pi_desc; bool pi_pending; u16 posted_intr_nv; @@ -253,20 +209,10 @@ struct nested_vmx { struct vcpu_vmx { struct kvm_vcpu vcpu; + struct vcpu_vt vt; u8 fail; u8 x2apic_msr_bitmap_mode; - /* - * If true, host state has been stored in vmx->loaded_vmcs for - * the CPU registers that only need to be switched when transitioning - * to/from the kernel, and the registers have been loaded with guest - * values. If false, host state is loaded in the CPU registers - * and vmx->loaded_vmcs->host_state is invalid. - */ - bool guest_state_loaded; - - unsigned long exit_qualification; - u32 exit_intr_info; u32 idt_vectoring_info; ulong rflags; @@ -279,7 +225,6 @@ struct vcpu_vmx { struct vmx_uret_msr guest_uret_msrs[MAX_NR_USER_RETURN_MSRS]; bool guest_uret_msrs_loaded; #ifdef CONFIG_X86_64 - u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; #endif @@ -318,15 +263,6 @@ struct vcpu_vmx { } seg[8]; } segment_cache; int vpid; - bool emulation_required; - - union vmx_exit_reason exit_reason; - - /* Posted interrupt descriptor */ - struct pi_desc pi_desc; - - /* Used if this vCPU is waiting for PI notification wakeup. */ - struct list_head pi_wakeup_list; /* Support for a guest hypervisor (nested VMX) */ struct nested_vmx nested; @@ -336,14 +272,15 @@ struct vcpu_vmx { bool ple_window_dirty; /* Support for PML */ -#define PML_ENTITY_NUM 512 +#define PML_LOG_NR_ENTRIES 512 + /* PML is written backwards: this is the first entry written by the CPU */ +#define PML_HEAD_INDEX (PML_LOG_NR_ENTRIES-1) + struct page *pml_pg; /* apic deadline value in host tsc */ u64 hv_deadline_tsc; - unsigned long host_debugctlmsr; - /* * Only bits masked by msr_ia32_feature_control_valid_bits can be set in * msr_ia32_feature_control. FEAT_CTL_LOCKED is always included @@ -365,6 +302,9 @@ struct vcpu_vmx { DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS); DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS); } shadow_msr_intercept; + + /* ve_info must be page aligned. */ + struct vmx_ve_information *ve_info; }; struct kvm_vmx { @@ -377,6 +317,43 @@ struct kvm_vmx { u64 *pid_table; }; +static __always_inline struct vcpu_vt *to_vt(struct kvm_vcpu *vcpu) +{ + return &(container_of(vcpu, struct vcpu_vmx, vcpu)->vt); +} + +static __always_inline struct kvm_vcpu *vt_to_vcpu(struct vcpu_vt *vt) +{ + return &(container_of(vt, struct vcpu_vmx, vt)->vcpu); +} + +static __always_inline union vmx_exit_reason vmx_get_exit_reason(struct kvm_vcpu *vcpu) +{ + return to_vt(vcpu)->exit_reason; +} + +static __always_inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu) +{ + struct vcpu_vt *vt = to_vt(vcpu); + + if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1) && + !WARN_ON_ONCE(is_td_vcpu(vcpu))) + vt->exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + + return vt->exit_qualification; +} + +static __always_inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu) +{ + struct vcpu_vt *vt = to_vt(vcpu); + + if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2) && + !WARN_ON_ONCE(is_td_vcpu(vcpu))) + vt->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + + return vt->exit_intr_info; +} + void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, struct loaded_vmcs *buddy); int allocate_vpid(void); @@ -386,6 +363,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, unsigned long fs_base, unsigned long gs_base); int vmx_get_cpl(struct kvm_vcpu *vcpu); +int vmx_get_cpl_no_cache(struct kvm_vcpu *vcpu); bool vmx_emulation_required(struct kvm_vcpu *vcpu); unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); @@ -403,6 +381,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu); void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); bool vmx_nmi_blocked(struct kvm_vcpu *vcpu); +bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu); bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu); bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); @@ -577,7 +556,8 @@ static inline u8 vmx_get_rvi(void) SECONDARY_EXEC_ENABLE_VMFUNC | \ SECONDARY_EXEC_BUS_LOCK_DETECTION | \ SECONDARY_EXEC_NOTIFY_VM_EXITING | \ - SECONDARY_EXEC_ENCLS_EXITING) + SECONDARY_EXEC_ENCLS_EXITING | \ + SECONDARY_EXEC_EPT_VIOLATION_VE) #define KVM_REQUIRED_VMX_TERTIARY_VM_EXEC_CONTROL 0 #define KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL \ @@ -660,45 +640,10 @@ static __always_inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_vmx, vcpu); } -static inline struct lbr_desc *vcpu_to_lbr_desc(struct kvm_vcpu *vcpu) -{ - return &to_vmx(vcpu)->lbr_desc; -} - -static inline struct x86_pmu_lbr *vcpu_to_lbr_records(struct kvm_vcpu *vcpu) -{ - return &vcpu_to_lbr_desc(vcpu)->records; -} - -static inline bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu) -{ - return !!vcpu_to_lbr_records(vcpu)->nr; -} - void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu); int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu); void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu); -static __always_inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1)) - vmx->exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - return vmx->exit_qualification; -} - -static __always_inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2)) - vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - - return vmx->exit_intr_info; -} - struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags); void free_vmcs(struct vmcs *vmcs); int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs); @@ -723,7 +668,7 @@ static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu) return true; return allow_smaller_maxphyaddr && - cpuid_maxphyaddr(vcpu) < kvm_get_shadow_phys_bits(); + cpuid_maxphyaddr(vcpu) < kvm_host.maxphyaddr; } static inline bool is_unrestricted_guest(struct kvm_vcpu *vcpu) @@ -751,4 +696,12 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && enable_ipiv; } +static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) +{ + vmx->segment_cache.bitmask = 0; +} + +int vmx_init(void); +void vmx_exit(void); + #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h index eb48153bfd73..cdf8cbb69209 100644 --- a/arch/x86/kvm/vmx/vmx_onhyperv.h +++ b/arch/x86/kvm/vmx/vmx_onhyperv.h @@ -3,7 +3,7 @@ #ifndef __ARCH_X86_KVM_VMX_ONHYPERV_H__ #define __ARCH_X86_KVM_VMX_ONHYPERV_H__ -#include <asm/hyperv-tlfs.h> +#include <hyperv/hvhdk.h> #include <asm/mshyperv.h> #include <linux/jump_label.h> @@ -104,6 +104,14 @@ static inline void evmcs_load(u64 phys_addr) struct hv_vp_assist_page *vp_ap = hv_get_vp_assist_page(smp_processor_id()); + /* + * When enabling eVMCS, KVM verifies that every CPU has a valid hv_vp_assist_page() + * and aborts enabling the feature otherwise. CPU onlining path is also checked in + * vmx_hardware_enable(). + */ + if (KVM_BUG_ON(!vp_ap, kvm_get_running_vcpu()->kvm)) + return; + if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) vp_ap->nested_control.features.directhypercall = 1; vp_ap->current_nested_vmcs = phys_addr; diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 8060e5fc6dbd..96677576c836 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -15,7 +15,7 @@ void vmwrite_error(unsigned long field, unsigned long value); void vmclear_error(struct vmcs *vmcs, u64 phys_addr); void vmptrld_error(struct vmcs *vmcs, u64 phys_addr); void invvpid_error(unsigned long ext, u16 vpid, gva_t gva); -void invept_error(unsigned long ext, u64 eptp, gpa_t gpa); +void invept_error(unsigned long ext, u64 eptp); #ifndef CONFIG_CC_HAS_ASM_GOTO_OUTPUT /* @@ -47,7 +47,7 @@ static __always_inline void vmcs_check16(unsigned long field) BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, "16-bit accessor invalid for 64-bit high field"); BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, - "16-bit accessor invalid for 32-bit high field"); + "16-bit accessor invalid for 32-bit field"); BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, "16-bit accessor invalid for natural width field"); } @@ -118,7 +118,7 @@ do_exception: #else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ - asm volatile("1: vmread %2, %1\n\t" + asm volatile("1: vmread %[field], %[output]\n\t" ".byte 0x3e\n\t" /* branch taken hint */ "ja 3f\n\t" @@ -127,24 +127,26 @@ do_exception: * @field, and bounce through the trampoline to preserve * volatile registers. */ - "xorl %k1, %k1\n\t" + "xorl %k[output], %k[output]\n\t" "2:\n\t" - "push %1\n\t" - "push %2\n\t" + "push %[output]\n\t" + "push %[field]\n\t" "call vmread_error_trampoline\n\t" /* * Unwind the stack. Note, the trampoline zeros out the * memory for @fault so that the result is '0' on error. */ - "pop %2\n\t" - "pop %1\n\t" + "pop %[field]\n\t" + "pop %[output]\n\t" "3:\n\t" /* VMREAD faulted. As above, except push '1' for @fault. */ - _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_ONE_REG, %1) + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_ONE_REG, %[output]) - : ASM_CALL_CONSTRAINT, "=&r"(value) : "r"(field) : "cc"); + : ASM_CALL_CONSTRAINT, [output] "=&r" (value) + : [field] "r" (field) + : "cc"); return value; #endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ @@ -312,13 +314,13 @@ static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva) vmx_asm2(invvpid, "r"(ext), "m"(operand), ext, vpid, gva); } -static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa) +static inline void __invept(unsigned long ext, u64 eptp) { struct { - u64 eptp, gpa; - } operand = {eptp, gpa}; - - vmx_asm2(invept, "r"(ext), "m"(operand), ext, eptp, gpa); + u64 eptp; + u64 reserved_0; + } operand = { eptp, 0 }; + vmx_asm2(invept, "r"(ext), "m"(operand), ext, eptp); } static inline void vpid_sync_vcpu_single(int vpid) @@ -355,13 +357,13 @@ static inline void vpid_sync_vcpu_addr(int vpid, gva_t addr) static inline void ept_sync_global(void) { - __invept(VMX_EPT_EXTENT_GLOBAL, 0, 0); + __invept(VMX_EPT_EXTENT_GLOBAL, 0); } static inline void ept_sync_context(u64 eptp) { if (cpu_has_vmx_invept_context()) - __invept(VMX_EPT_EXTENT_CONTEXT, eptp, 0); + __invept(VMX_EPT_EXTENT_CONTEXT, eptp); else ept_sync_global(); } diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h new file mode 100644 index 000000000000..6bf8be570b2e --- /dev/null +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -0,0 +1,233 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_VMX_X86_OPS_H +#define __KVM_X86_VMX_X86_OPS_H + +#include <linux/kvm_host.h> + +#include "x86.h" + +__init int vmx_hardware_setup(void); + +extern struct kvm_x86_ops vt_x86_ops __initdata; +extern struct kvm_x86_init_ops vt_init_ops __initdata; + +void vmx_hardware_unsetup(void); +int vmx_check_processor_compat(void); +int vmx_enable_virtualization_cpu(void); +void vmx_disable_virtualization_cpu(void); +void vmx_emergency_disable_virtualization_cpu(void); +int vmx_vm_init(struct kvm *kvm); +void vmx_vm_destroy(struct kvm *kvm); +int vmx_vcpu_precreate(struct kvm *kvm); +int vmx_vcpu_create(struct kvm_vcpu *vcpu); +int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu); +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit); +void vmx_vcpu_free(struct kvm_vcpu *vcpu); +void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); +void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu); +void vmx_vcpu_put(struct kvm_vcpu *vcpu); +int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath); +void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu); +int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu); +void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu); +int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); +#ifdef CONFIG_KVM_SMM +int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection); +int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram); +int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram); +void vmx_enable_smi_window(struct kvm_vcpu *vcpu); +#endif +int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len); +int vmx_check_intercept(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage, + struct x86_exception *exception); +bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu); +void vmx_migrate_timers(struct kvm_vcpu *vcpu); +void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); +void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); +int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu); +void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector); +void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu); +bool vmx_has_emulated_msr(struct kvm *kvm, u32 index); +void vmx_msr_filter_changed(struct kvm_vcpu *vcpu); +void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); +void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); +int vmx_get_feature_msr(u32 msr, u64 *data); +int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); +u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg); +void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); +void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); +int vmx_get_cpl(struct kvm_vcpu *vcpu); +void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); +bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); +void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer); +void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val); +void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val); +void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu); +void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg); +unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); +void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); +bool vmx_get_if_flag(struct kvm_vcpu *vcpu); +void vmx_flush_tlb_all(struct kvm_vcpu *vcpu); +void vmx_flush_tlb_current(struct kvm_vcpu *vcpu); +void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr); +void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu); +void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask); +u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu); +void vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall); +void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected); +void vmx_inject_nmi(struct kvm_vcpu *vcpu); +void vmx_inject_exception(struct kvm_vcpu *vcpu); +void vmx_cancel_injection(struct kvm_vcpu *vcpu); +int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection); +int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection); +bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); +void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); +void vmx_enable_nmi_window(struct kvm_vcpu *vcpu); +void vmx_enable_irq_window(struct kvm_vcpu *vcpu); +void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr); +void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu); +void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); +void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); +int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); +int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr); +u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); + +void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code); +void vmx_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code); + +u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu); +u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu); +void vmx_write_tsc_offset(struct kvm_vcpu *vcpu); +void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu); +void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); +#ifdef CONFIG_X86_64 +int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, + bool *expired); +void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu); +#endif +void vmx_setup_mce(struct kvm_vcpu *vcpu); + +#ifdef CONFIG_KVM_INTEL_TDX +void tdx_disable_virtualization_cpu(void); +int tdx_vm_init(struct kvm *kvm); +void tdx_mmu_release_hkid(struct kvm *kvm); +void tdx_vm_destroy(struct kvm *kvm); +int tdx_vm_ioctl(struct kvm *kvm, void __user *argp); + +int tdx_vcpu_create(struct kvm_vcpu *vcpu); +void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); +void tdx_vcpu_free(struct kvm_vcpu *vcpu); +void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu); +int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu); +fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit); +void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); +void tdx_vcpu_put(struct kvm_vcpu *vcpu); +bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu); +int tdx_handle_exit(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion fastpath); + +void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector); +void tdx_inject_nmi(struct kvm_vcpu *vcpu); +void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code); +bool tdx_has_emulated_msr(u32 index); +int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); +int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); + +int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp); + +int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn, + enum pg_level level, void *private_spt); +int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn, + enum pg_level level, void *private_spt); +int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn, + enum pg_level level, kvm_pfn_t pfn); +int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, + enum pg_level level, kvm_pfn_t pfn); + +void tdx_flush_tlb_current(struct kvm_vcpu *vcpu); +void tdx_flush_tlb_all(struct kvm_vcpu *vcpu); +void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); +int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn); +#else +static inline void tdx_disable_virtualization_cpu(void) {} +static inline int tdx_vm_init(struct kvm *kvm) { return -EOPNOTSUPP; } +static inline void tdx_mmu_release_hkid(struct kvm *kvm) {} +static inline void tdx_vm_destroy(struct kvm *kvm) {} +static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; } + +static inline int tdx_vcpu_create(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; } +static inline void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) {} +static inline void tdx_vcpu_free(struct kvm_vcpu *vcpu) {} +static inline void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) {} +static inline int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; } +static inline fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) +{ + return EXIT_FASTPATH_NONE; +} +static inline void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) {} +static inline void tdx_vcpu_put(struct kvm_vcpu *vcpu) {} +static inline bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu) { return false; } +static inline int tdx_handle_exit(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion fastpath) { return 0; } + +static inline void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) {} +static inline void tdx_inject_nmi(struct kvm_vcpu *vcpu) {} +static inline void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1, + u64 *info2, u32 *intr_info, u32 *error_code) {} +static inline bool tdx_has_emulated_msr(u32 index) { return false; } +static inline int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; } +static inline int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; } + +static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; } + +static inline int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn, + enum pg_level level, + void *private_spt) +{ + return -EOPNOTSUPP; +} + +static inline int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn, + enum pg_level level, + void *private_spt) +{ + return -EOPNOTSUPP; +} + +static inline int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn, + enum pg_level level, + kvm_pfn_t pfn) +{ + return -EOPNOTSUPP; +} + +static inline int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, + enum pg_level level, + kvm_pfn_t pfn) +{ + return -EOPNOTSUPP; +} + +static inline void tdx_flush_tlb_current(struct kvm_vcpu *vcpu) {} +static inline void tdx_flush_tlb_all(struct kvm_vcpu *vcpu) {} +static inline void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) {} +static inline int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) { return 0; } +#endif + +#endif /* __KVM_X86_VMX_X86_OPS_H */ |