diff options
| -rw-r--r-- | arch/x86/include/asm/kvm-x86-ops.h | 1 | ||||
| -rw-r--r-- | arch/x86/include/asm/kvm_host.h | 1 | ||||
| -rw-r--r-- | arch/x86/include/asm/posted_intr.h | 5 | ||||
| -rw-r--r-- | arch/x86/include/uapi/asm/vmx.h | 1 | ||||
| -rw-r--r-- | arch/x86/kvm/irq.c | 3 | ||||
| -rw-r--r-- | arch/x86/kvm/lapic.c | 14 | ||||
| -rw-r--r-- | arch/x86/kvm/lapic.h | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/smm.h | 3 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/common.h | 70 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/main.c | 260 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/nested.c | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/posted_intr.c | 9 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/posted_intr.h | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/tdx.c | 131 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/tdx.h | 5 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 113 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.h | 1 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/x86_ops.h | 13 | ||||
| -rw-r--r-- | arch/x86/kvm/x86.c | 6 |
19 files changed, 522 insertions, 120 deletions
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index aae4193f80e3..79406bf07a1c 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -116,6 +116,7 @@ KVM_X86_OP_OPTIONAL(pi_start_assignment) KVM_X86_OP_OPTIONAL(apicv_pre_state_restore) KVM_X86_OP_OPTIONAL(apicv_post_state_restore) KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt) +KVM_X86_OP_OPTIONAL(protected_apic_has_interrupt) KVM_X86_OP_OPTIONAL(set_hv_timer) KVM_X86_OP_OPTIONAL(cancel_hv_timer) KVM_X86_OP(setup_mce) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3a6373fc58a1..7fdbe84374f4 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1842,6 +1842,7 @@ struct kvm_x86_ops { void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); + bool (*protected_apic_has_interrupt)(struct kvm_vcpu *vcpu); int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, bool *expired); diff --git a/arch/x86/include/asm/posted_intr.h b/arch/x86/include/asm/posted_intr.h index de788b400fba..bb107ebbe713 100644 --- a/arch/x86/include/asm/posted_intr.h +++ b/arch/x86/include/asm/posted_intr.h @@ -81,6 +81,11 @@ static inline bool pi_test_sn(struct pi_desc *pi_desc) return test_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); } +static inline bool pi_test_pir(int vector, struct pi_desc *pi_desc) +{ + return test_bit(vector, (unsigned long *)pi_desc->pir); +} + /* Non-atomic helpers */ static inline void __pi_set_sn(struct pi_desc *pi_desc) { diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 6a9f268a2d2c..f0f4a4cf84a7 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -34,6 +34,7 @@ #define EXIT_REASON_TRIPLE_FAULT 2 #define EXIT_REASON_INIT_SIGNAL 3 #define EXIT_REASON_SIPI_SIGNAL 4 +#define EXIT_REASON_OTHER_SMI 6 #define EXIT_REASON_INTERRUPT_WINDOW 7 #define EXIT_REASON_NMI_WINDOW 8 diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 63f66c51975a..97d68d837929 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -100,6 +100,9 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) if (kvm_cpu_has_extint(v)) return 1; + if (lapic_in_kernel(v) && v->arch.apic->guest_apic_protected) + return kvm_x86_call(protected_apic_has_interrupt)(v); + return kvm_apic_has_interrupt(v) != -1; /* LAPIC */ } EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index a1cbca31ec30..e78b1d223230 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1797,8 +1797,17 @@ static void apic_update_lvtt(struct kvm_lapic *apic) static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - u32 reg = kvm_lapic_get_reg(apic, APIC_LVTT); + u32 reg; + /* + * Assume a timer IRQ was "injected" if the APIC is protected. KVM's + * copy of the vIRR is bogus, it's the responsibility of the caller to + * precisely check whether or not a timer IRQ is pending. + */ + if (apic->guest_apic_protected) + return true; + + reg = kvm_lapic_get_reg(apic, APIC_LVTT); if (kvm_apic_hw_enabled(apic)) { int vec = reg & APIC_VECTOR_MASK; void *bitmap = apic->regs + APIC_ISR; @@ -2967,6 +2976,9 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) if (!kvm_apic_present(vcpu)) return -1; + if (apic->guest_apic_protected) + return -1; + __apic_update_ppr(apic, &ppr); return apic_has_interrupt_for_ppr(apic, ppr); } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 1a8553ebdb42..e33c969439f7 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -65,6 +65,8 @@ struct kvm_lapic { bool sw_enabled; bool irr_pending; bool lvt0_in_nmi_mode; + /* Select registers in the vAPIC cannot be read/written. */ + bool guest_apic_protected; /* Number of bits set in ISR. */ s16 isr_count; /* The highest vector set in ISR; if -1 - invalid, must scan ISR. */ diff --git a/arch/x86/kvm/smm.h b/arch/x86/kvm/smm.h index a1cf2ac5bd78..551703fbe200 100644 --- a/arch/x86/kvm/smm.h +++ b/arch/x86/kvm/smm.h @@ -142,6 +142,9 @@ union kvm_smram { static inline int kvm_inject_smi(struct kvm_vcpu *vcpu) { + if (!kvm_x86_call(has_emulated_msr)(vcpu->kvm, MSR_IA32_SMBASE)) + return -ENOTTY; + kvm_make_request(KVM_REQ_SMI, vcpu); return 0; } diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h index a298ac795c09..8fe6a7fa1c68 100644 --- a/arch/x86/kvm/vmx/common.h +++ b/arch/x86/kvm/vmx/common.h @@ -48,6 +48,7 @@ struct vcpu_vt { * hardware. */ bool guest_state_loaded; + bool emulation_required; #ifdef CONFIG_X86_64 u64 msr_host_kernel_gs_base; @@ -109,4 +110,73 @@ static inline int __vmx_handle_ept_violation(struct kvm_vcpu *vcpu, gpa_t gpa, 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/main.c b/arch/x86/kvm/vmx/main.c index a567865baf9b..67d51925b2f6 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -62,6 +62,7 @@ static __init int vt_hardware_setup(void) 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; @@ -117,8 +118,10 @@ static void vt_vcpu_free(struct kvm_vcpu *vcpu) static void vt_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { - if (is_td_vcpu(vcpu)) + if (is_td_vcpu(vcpu)) { + tdx_vcpu_reset(vcpu, init_event); return; + } vmx_vcpu_reset(vcpu, init_event); } @@ -190,6 +193,98 @@ static int vt_handle_exit(struct kvm_vcpu *vcpu, return vmx_handle_exit(vcpu, fastpath); } +#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 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_flush_tlb_all(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) { @@ -226,6 +321,57 @@ static void vt_flush_tlb_guest(struct kvm_vcpu *vcpu) 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) { @@ -237,6 +383,54 @@ static void vt_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, 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_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) +{ + if (is_td_vcpu(vcpu)) + return; + + vmx_inject_irq(vcpu, reinjected); +} + +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 true; + + 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; @@ -260,6 +454,24 @@ static void vt_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, vmx_get_exit_info(vcpu, reason, info1, info2, intr_info, error_code); } +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 int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp) { if (!is_td(kvm)) @@ -358,31 +570,31 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .handle_exit = vt_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, + .set_interrupt_shadow = vt_set_interrupt_shadow, + .get_interrupt_shadow = vt_get_interrupt_shadow, .patch_hypercall = vmx_patch_hypercall, - .inject_irq = vmx_inject_irq, - .inject_nmi = vmx_inject_nmi, + .inject_irq = vt_inject_irq, + .inject_nmi = vt_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, + .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 = vmx_update_cr8_intercept, .x2apic_icr_is_split = false, - .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, + .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 = vmx_load_eoi_exitmap, - .apicv_pre_state_restore = vmx_apicv_pre_state_restore, + .apicv_pre_state_restore = vt_apicv_pre_state_restore, .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, - .hwapic_isr_update = vmx_hwapic_isr_update, - .sync_pir_to_irr = vmx_sync_pir_to_irr, - .deliver_interrupt = vmx_deliver_interrupt, + .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 = vmx_set_tss_addr, @@ -421,14 +633,14 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .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, + .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 = vmx_check_emulate_instruction, - .apic_init_signal_blocked = vmx_apic_init_signal_blocked, + .apic_init_signal_blocked = vt_apic_init_signal_blocked, .migrate_timers = vmx_migrate_timers, .msr_filter_changed = vmx_msr_filter_changed, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 99f02972cd74..5b5d6017cb3d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4794,7 +4794,7 @@ 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) diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 5696e0f9f924..895bbe85b818 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() @@ -31,7 +32,7 @@ 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) +struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) { return &(to_vt(vcpu)->pi_desc); } @@ -190,7 +191,8 @@ 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 +202,8 @@ 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) || !vmx_interrupt_blocked(vcpu))) pi_enable_wakeup_handler(vcpu); /* diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index ad9116a99bcc..68605ca7ef68 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -5,6 +5,8 @@ #include <linux/bitmap.h> #include <asm/posted_intr.h> +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); void pi_wakeup_handler(void); diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 35f28e165417..8b00639680dc 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -15,6 +15,7 @@ #include "mmu/spte.h" #include "common.h" #include "posted_intr.h" +#include "irq.h" #include <trace/events/kvm.h> #include "trace.h" @@ -644,11 +645,17 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu) if (kvm_tdx->state != TD_STATE_INITIALIZED) return -EIO; - /* TDX module mandates APICv, which requires an in-kernel local APIC. */ - if (!lapic_in_kernel(vcpu)) + /* + * 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; @@ -669,6 +676,9 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu) 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; @@ -678,6 +688,7 @@ 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; @@ -695,6 +706,11 @@ void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) local_irq_enable(); } +bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu) +{ + return pi_has_pending_interrupt(vcpu); +} + /* * 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. @@ -866,6 +882,8 @@ static noinstr void tdx_vcpu_enter_exit(struct kvm_vcpu *vcpu) 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(); } @@ -958,6 +976,14 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) 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) @@ -982,6 +1008,47 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) 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); @@ -1621,6 +1688,18 @@ int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, 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); +} + int tdx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t fastpath) { struct vcpu_tdx *tdx = to_tdx(vcpu); @@ -1666,6 +1745,11 @@ int tdx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t fastpath) 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_TDCALL: return handle_tdvmcall(vcpu); case EXIT_REASON_VMCALL: @@ -1674,6 +1758,27 @@ int tdx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t fastpath) return tdx_emulate_io(vcpu); case EXIT_REASON_EPT_MISCONFIG: return tdx_emulate_mmio(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; } @@ -2564,11 +2669,28 @@ static int tdx_vcpu_init(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd) 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; @@ -2983,6 +3105,11 @@ int __init tdx_bringup(void) 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; diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h index 3aa36ddcd472..93858959baf9 100644 --- a/arch/x86/kvm/vmx/tdx.h +++ b/arch/x86/kvm/vmx/tdx.h @@ -115,6 +115,8 @@ static __always_inline void tdvps_vmcs_check(u32 field, u8 bits) "Invalid TD VMCS access for 16-bit field"); } +static __always_inline void tdvps_management_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) \ @@ -164,6 +166,9 @@ static __always_inline void td_##lclass##_clearbit##bits(struct vcpu_tdx *tdx, \ 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); + #else static inline int tdx_bringup(void) { return 0; } static inline void tdx_cleanup(void) {} diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e7e451209306..71476a33f4f2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1580,7 +1580,7 @@ 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); } bool vmx_get_if_flag(struct kvm_vcpu *vcpu) @@ -1862,7 +1862,7 @@ 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, @@ -3391,7 +3391,7 @@ 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) @@ -3654,7 +3654,7 @@ 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); } void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) @@ -4182,50 +4182,6 @@ 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) { @@ -4285,20 +4241,7 @@ 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, &vt->pi_desc)) - return 0; - - /* If a previous notification has sent the IPI, nothing to do. */ - if (pi_test_and_set_on(&vt->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; } @@ -5857,7 +5800,7 @@ static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - return vmx->emulation_required && !vmx->rmode.vm86_active && + return vmx->vt.emulation_required && !vmx->rmode.vm86_active && (kvm_is_exception_pending(vcpu) || vcpu->arch.exception.injected); } @@ -5870,7 +5813,7 @@ 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); @@ -6517,7 +6460,7 @@ 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; } @@ -6527,7 +6470,7 @@ 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) { @@ -6961,14 +6904,6 @@ void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } -void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu) -{ - struct vcpu_vt *vt = to_vt(vcpu); - - pi_clear_on(&vt->pi_desc); - memset(vt->pi_desc.pir, 0, sizeof(vt->pi_desc.pir)); -} - void vmx_do_interrupt_irqoff(unsigned long entry); void vmx_do_nmi_irqoff(void); @@ -7026,9 +6961,7 @@ static void handle_external_interrupt_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_get_exit_reason(vcpu).basic == EXIT_REASON_EXTERNAL_INTERRUPT) @@ -7279,6 +7212,20 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu, } } +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) { @@ -7322,15 +7269,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, if (likely(!vmx_get_exit_reason(vcpu).failed_vmentry)) vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - if ((u16)vmx_get_exit_reason(vcpu).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(); @@ -7351,7 +7290,7 @@ 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->vt.exit_reason.full = EXIT_REASON_INVALID_STATE; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index e635199901e2..6d1e40ecc024 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -263,7 +263,6 @@ struct vcpu_vmx { } seg[8]; } segment_cache; int vpid; - bool emulation_required; /* Support for a guest hypervisor (nested VMX) */ struct nested_vmx nested; diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index 2960d95c2c78..c792ea66a45f 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -46,7 +46,6 @@ int vmx_check_intercept(struct kvm_vcpu *vcpu, 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_apicv_pre_state_restore(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, @@ -129,14 +128,20 @@ 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); @@ -163,6 +168,7 @@ 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; } @@ -172,8 +178,13 @@ static inline fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediat } 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) {} diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5c37bc4fb80e..2ed3122f484f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5114,6 +5114,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { + if (vcpu->arch.apic->guest_apic_protected) + return -EINVAL; + kvm_x86_call(sync_pir_to_irr)(vcpu); return kvm_apic_get_state(vcpu, s); @@ -5124,6 +5127,9 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, { int r; + if (vcpu->arch.apic->guest_apic_protected) + return -EINVAL; + r = kvm_apic_set_state(vcpu, s); if (r) return r; |