From: Sean Christopherson <sean.j.christopherson@xxxxxxxxx> TDX handles NMI/exception exit mostly the same as VMX case. The difference is how to retrieve exit qualification. To share the code with TDX, move NMI/exception to a common header, common.h. No functional change intended. Signed-off-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx> Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx> Co-developed-by: Binbin Wu <binbin.wu@xxxxxxxxxxxxxxx> Signed-off-by: Binbin Wu <binbin.wu@xxxxxxxxxxxxxxx> --- TDX interrupts breakout: - Update change log with suggestions from (Binbin) - Move the NMI handling code to common header and add a helper __vmx_handle_nmi() for it. (Binbin) --- arch/x86/kvm/vmx/common.h | 72 ++++++++++++++++++++++++++++++++++++ arch/x86/kvm/vmx/vmx.c | 77 +++++---------------------------------- 2 files changed, 82 insertions(+), 67 deletions(-) diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h index a46f15ddeda1..809ced4c6cd8 100644 --- a/arch/x86/kvm/vmx/common.h +++ b/arch/x86/kvm/vmx/common.h @@ -4,8 +4,70 @@ #include <linux/kvm_host.h> +#include <asm/traps.h> +#include <asm/fred.h> + #include "posted_intr.h" #include "mmu.h" +#include "vmcs.h" +#include "x86.h" + +extern unsigned long vmx_host_idt_base; +void vmx_do_interrupt_irqoff(unsigned long entry); +void vmx_do_nmi_irqoff(void); + +static inline void vmx_handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) +{ + /* + * Save xfd_err to guest_fpu before interrupt is enabled, so the + * 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. + * + * 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. + */ + if (vcpu->arch.guest_fpu.fpstate->xfd) + rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); +} + +static inline void vmx_handle_exception_irqoff(struct kvm_vcpu *vcpu, + u32 intr_info) +{ + /* if exit due to PF check for async PF */ + if (is_page_fault(intr_info)) + 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)) + vmx_handle_nm_fault_irqoff(vcpu); + /* Handle machine checks before interrupts are enabled */ + else if (is_machine_check(intr_info)) + kvm_machine_check(); +} + +static inline void vmx_handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu, + u32 intr_info) +{ + unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; + + if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, + "unexpected VM-Exit interrupt info: 0x%x", intr_info)) + return; + + kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector); + else + vmx_do_interrupt_irqoff(gate_offset((gate_desc *)vmx_host_idt_base + vector)); + kvm_after_interrupt(vcpu); + + vcpu->arch.at_instruction_boundary = true; +} static inline bool vt_is_tdx_private_gpa(struct kvm *kvm, gpa_t gpa) { @@ -111,4 +173,14 @@ static inline void __vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, kvm_vcpu_trigger_posted_interrupt(vcpu, POSTED_INTR_VECTOR); } +static __always_inline void __vmx_handle_nmi(struct kvm_vcpu *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); +} + #endif /* __KVM_X86_VMX_COMMON_H */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 75432e1c9f7f..d2f926d85c3e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -527,7 +527,7 @@ static const struct kvm_vmx_segment_field { }; -static unsigned long host_idt_base; +unsigned long vmx_host_idt_base; #if IS_ENABLED(CONFIG_HYPERV) static bool __read_mostly enlightened_vmcs = true; @@ -4290,7 +4290,7 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */ - vmcs_writel(HOST_IDTR_BASE, host_idt_base); /* 22.2.4 */ + vmcs_writel(HOST_IDTR_BASE, vmx_host_idt_base); /* 22.2.4 */ vmcs_writel(HOST_RIP, (unsigned long)vmx_vmexit); /* 22.2.5 */ @@ -5160,7 +5160,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) intr_info = vmx_get_intr_info(vcpu); /* - * Machine checks are handled by handle_exception_irqoff(), or by + * Machine checks are handled by vmx_handle_exception_irqoff(), or by * vmx_vcpu_run() if a #MC occurs on VM-Entry. NMIs are handled by * vmx_vcpu_enter_exit(). */ @@ -5168,7 +5168,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) return 1; /* - * Queue the exception here instead of in handle_nm_fault_irqoff(). + * Queue the exception here instead of in vmx_handle_nm_fault_irqoff(). * This ensures the nested_vmx check is not skipped so vmexit can * be reflected to L1 (when it intercepts #NM) before reaching this * point. @@ -6887,58 +6887,6 @@ void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) void vmx_do_interrupt_irqoff(unsigned long entry); void vmx_do_nmi_irqoff(void); -static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) -{ - /* - * Save xfd_err to guest_fpu before interrupt is enabled, so the - * 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. - * - * 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. - */ - if (vcpu->arch.guest_fpu.fpstate->xfd) - rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); -} - -static void handle_exception_irqoff(struct kvm_vcpu *vcpu, u32 intr_info) -{ - /* if exit due to PF check for async PF */ - if (is_page_fault(intr_info)) - 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(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, - u32 intr_info) -{ - unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; - - if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, - "unexpected VM-Exit interrupt info: 0x%x", intr_info)) - return; - - kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); - if (cpu_feature_enabled(X86_FEATURE_FRED)) - fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector); - else - vmx_do_interrupt_irqoff(gate_offset((gate_desc *)host_idt_base + vector)); - kvm_after_interrupt(vcpu); - - vcpu->arch.at_instruction_boundary = true; -} - void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6947,9 +6895,10 @@ void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) return; if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) - handle_external_interrupt_irqoff(vcpu, vmx_get_intr_info(vcpu)); + vmx_handle_external_interrupt_irqoff(vcpu, + vmx_get_intr_info(vcpu)); else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI) - handle_exception_irqoff(vcpu, vmx_get_intr_info(vcpu)); + vmx_handle_exception_irqoff(vcpu, vmx_get_intr_info(vcpu)); } /* @@ -7238,14 +7187,8 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, 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); - } + is_nmi(vmx_get_intr_info(vcpu))) + __vmx_handle_nmi(vcpu); out: guest_state_exit_irqoff(); @@ -8309,7 +8252,7 @@ __init int vmx_hardware_setup(void) int r; store_idt(&dt); - host_idt_base = dt.address; + vmx_host_idt_base = dt.address; vmx_setup_user_return_msrs(); -- 2.46.0