@@ -129,6 +129,11 @@ static inline bool is_machine_check(u32 intr_info)
return is_exception_n(intr_info, MC_VECTOR);
}
+static inline bool is_nm(u32 intr_info)
+{
+ return is_exception_n(intr_info, NM_VECTOR);
+}
+
/* Undocumented: icebp/int1 */
static inline bool is_icebp(u32 intr_info)
{
@@ -36,6 +36,7 @@
#include <asm/debugreg.h>
#include <asm/desc.h>
#include <asm/fpu/api.h>
+#include <asm/fpu/xstate.h>
#include <asm/idtentry.h>
#include <asm/io.h>
#include <asm/irq_remapping.h>
@@ -763,6 +764,9 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu)
vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, match);
}
+ if (vcpu->arch.guest_supported_xcr0 & XFEATURE_MASK_USER_DYNAMIC)
+ eb |= (1u << NM_VECTOR);
+
vmcs_write32(EXCEPTION_BITMAP, eb);
}
@@ -4750,7 +4754,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
vect_info = vmx->idt_vectoring_info;
intr_info = vmx_get_intr_info(vcpu);
- if (is_machine_check(intr_info) || is_nmi(intr_info))
+ if (is_machine_check(intr_info) || is_nmi(intr_info) || is_nm(intr_info))
return 1; /* handled by handle_exception_nmi_irqoff() */
if (is_invalid_opcode(intr_info))
@@ -6338,6 +6342,12 @@ static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu,
kvm_after_interrupt(vcpu);
}
+static void handle_exception_nm(struct kvm_vcpu *vcpu)
+{
+ rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
+ kvm_queue_exception(vcpu, NM_VECTOR);
+}
+
static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
{
const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist;
@@ -6346,6 +6356,9 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
/* 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();
+ /* if exit due to NM, handle before preemptions are enabled */
+ else if (is_nm(intr_info))
+ handle_exception_nm(&vmx->vcpu);
/* Handle machine checks before interrupts are enabled */
else if (is_machine_check(intr_info))
kvm_machine_check();
@@ -9894,6 +9894,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (test_thread_flag(TIF_NEED_FPU_LOAD))
switch_fpu_return();
+ if (vcpu->arch.guest_fpu.xfd_err)
+ wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
+
if (unlikely(vcpu->arch.switch_db_regs)) {
set_debugreg(0, 7);
set_debugreg(vcpu->arch.eff_db[0], 0);
@@ -9957,6 +9960,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
static_call(kvm_x86_handle_exit_irqoff)(vcpu);
+ if (vcpu->arch.guest_fpu.xfd_err)
+ wrmsrl(MSR_IA32_XFD_ERR, 0);
+
/*
* Consume any pending interrupts, including the possible source of
* VM-Exit on SVM and any ticks that occur between VM-Exit and now.
Guest IA32_XFD_ERR is generally modified in two places: - Set by CPU when #NM is triggered; - Cleared by guest in its #NM handler; Intercept #NM for the first case, if guest CPUID includes any dynamic xfeature. #NM is rare if the guest doesn't use dynamic features. Otherwise, there is at most one exception per guest task given a dynamic feature. Save the current XFD_ERR value to the guest_fpu container in the #NM VM-exit handler. This must be done with interrupt/preemption disabled, otherwise the unsaved MSR value may be clobbered by host operations. Inject a virtual #NM to the guest after saving the MSR value. Restore the host value (always ZERO outside of the host #NM handler) before enabling preemption. Restore the guest value from the guest_fpu container right before entering the guest (with preemption disabled). Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Jing Liu <jing2.liu@intel.com> --- TODO: Investigate delaying #NM interception until guest sets a dynamic feature in XCR0. arch/x86/kvm/vmx/vmcs.h | 5 +++++ arch/x86/kvm/vmx/vmx.c | 15 ++++++++++++++- arch/x86/kvm/x86.c | 6 ++++++ 3 files changed, 25 insertions(+), 1 deletion(-)