summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/vmx/vmx.c
diff options
context:
space:
mode:
authorJing Liu <jing2.liu@intel.com>2022-01-05 04:35:23 -0800
committerPaolo Bonzini <pbonzini@redhat.com>2022-01-14 13:44:18 -0500
commitec5be88ab29fd9145c7ced20b58fb96f7c6b6890 (patch)
tree06aec550f4d361a24e520c8a60cd1b8a25630fa7 /arch/x86/kvm/vmx/vmx.c
parent1df4fd834e8e2c00973ac2003ad0e6feb8750b31 (diff)
downloadlinux-ec5be88ab29fd9145c7ced20b58fb96f7c6b6890.tar.bz2
kvm: x86: Intercept #NM for saving IA32_XFD_ERR
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 when a nonzero value is written to IA32_XFD. Nonzero indicates that the guest is willing to do dynamic fpstate expansion for certain xfeatures, thus KVM needs to manage and virtualize guest XFD_ERR properly. The vcpu exception bitmap is updated in XFD write emulation according to guest_fpu::xfd. Save the current XFD_ERR value to the guest_fpu container in the #NM VM-exit handler. This must be done with interrupt disabled, otherwise the unsaved MSR value may be clobbered by host activity. The saving operation is conducted conditionally only when guest_fpu:xfd includes a non-zero value. Doing so also avoids misread on a platform which doesn't support XFD but #NM is triggered due to L1 interception. Queueing #NM to the guest is postponed to handle_exception_nmi(). This goes through the nested_vmx check so a virtual vmexit is queued instead when #NM is triggered in L2 but L1 wants to intercept it. Restore the host value (always ZERO outside of the host #NM handler) before enabling interrupt. Restore the guest value from the guest_fpu container right before entering the guest (with interrupt disabled). Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Jing Liu <jing2.liu@intel.com> Signed-off-by: Kevin Tian <kevin.tian@intel.com> Signed-off-by: Yang Zhong <yang.zhong@intel.com> Message-Id: <20220105123532.12586-13-yang.zhong@intel.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'arch/x86/kvm/vmx/vmx.c')
-rw-r--r--arch/x86/kvm/vmx/vmx.c48
1 files changed, 48 insertions, 0 deletions
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 7b5abe25e1e5..84f6904cdb6e 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -36,6 +36,7 @@
#include <asm/debugreg.h>
#include <asm/desc.h>
#include <asm/fpu/api.h>
+#include <asm/fpu/xstate.h>
#include <asm/idtentry.h>
#include <asm/io.h>
#include <asm/irq_remapping.h>
@@ -761,6 +762,13 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu)
vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, match);
}
+ /*
+ * Trap #NM if guest xfd contains a non-zero value so guest XFD_ERR
+ * can be saved timely.
+ */
+ if (vcpu->arch.guest_fpu.fpstate->xfd)
+ eb |= (1u << NM_VECTOR);
+
vmcs_write32(EXCEPTION_BITMAP, eb);
}
@@ -1967,6 +1975,12 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_KERNEL_GS_BASE:
vmx_write_guest_kernel_gs_base(vmx, data);
break;
+ case MSR_IA32_XFD:
+ ret = kvm_set_msr_common(vcpu, msr_info);
+ /* Update #NM interception according to guest xfd */
+ if (!ret)
+ vmx_update_exception_bitmap(vcpu);
+ break;
#endif
case MSR_IA32_SYSENTER_CS:
if (is_guest_mode(vcpu))
@@ -4798,6 +4812,17 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
if (is_machine_check(intr_info) || is_nmi(intr_info))
return 1; /* handled by handle_exception_nmi_irqoff() */
+ /*
+ * Queue the exception here instead of in 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.
+ */
+ if (is_nm_fault(intr_info)) {
+ kvm_queue_exception(vcpu, NM_VECTOR);
+ return 1;
+ }
+
if (is_invalid_opcode(intr_info))
return handle_ud(vcpu);
@@ -6399,6 +6424,26 @@ static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu,
kvm_after_interrupt(vcpu);
}
+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_nmi_irqoff(struct vcpu_vmx *vmx)
{
const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist;
@@ -6407,6 +6452,9 @@ 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 interrupts are enabled */
+ else if (is_nm_fault(intr_info))
+ handle_nm_fault_irqoff(&vmx->vcpu);
/* Handle machine checks before interrupts are enabled */
else if (is_machine_check(intr_info))
kvm_machine_check();