[v4,12/21] kvm: x86: Intercept #NM for saving IA32_XFD_ERR

Commit Message

Yang Zhong Dec. 29, 2021, 1:13 p.m. UTC

From: Jing Liu <[e-mail]>

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 according to guest_fpu::xfd in XFD write emulation.

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 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 interrupt.

Restore the guest value from the guest_fpu container right before
entering the guest (with interrupt disabled).

Suggested-by: Thomas Gleixner <[e-mail]>
Signed-off-by: Jing Liu <[e-mail]>
Signed-off-by: Kevin Tian <[e-mail]>
Signed-off-by: Yang Zhong <[e-mail]>
---
 arch/x86/kvm/vmx/vmcs.h |  5 +++++
 arch/x86/kvm/vmx/vmx.c  | 26 +++++++++++++++++++++++++-
 arch/x86/kvm/x86.c      |  6 ++++++
 3 files changed, 36 insertions(+), 1 deletion(-)

Comments

Sean Christopherson Jan. 4, 2022, 8:01 p.m. UTC | #1

On Wed, Dec 29, 2021, Yang Zhong wrote:
> +static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu)
> +{
> +	rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
> +	kvm_queue_exception(vcpu, NM_VECTOR);

This is still wrong, even though no additional supported is needed to support
nested XFD.  If L1 wants to intercept #NM, then KVM must not inject the #NM and
must not read XFD_ERR.

That this was posted multiple times is disturbing, because kvm-unit-tests has a
test for exactly this, and running it against this series on a host without XFD
yields:

  unchecked MSR access error: RDMSR from 0x1c5 at rIP: 0xffffffffa02478ee (vmx_handle_exit_irqoff+0x1de/0x240 [kvm_intel])
  Call Trace:
   <TASK>
   kvm_arch_vcpu_ioctl_run+0x11a0/0x1fb0 [kvm]
   kvm_vcpu_ioctl+0x279/0x690 [kvm]
   __x64_sys_ioctl+0x83/0xb0
   do_syscall_64+0x3b/0xc0
   entry_SYSCALL_64_after_hwframe+0x44/0xae
   </TASK>

Tian, Kevin Jan. 5, 2022, 12:27 a.m. UTC | #2

> From: Sean Christopherson <[e-mail]>
> Sent: Wednesday, January 5, 2022 4:01 AM
> 
> On Wed, Dec 29, 2021, Yang Zhong wrote:
> > +static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu)
> > +{
> > +	rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
> > +	kvm_queue_exception(vcpu, NM_VECTOR);
> 
> This is still wrong, even though no additional supported is needed to support
> nested XFD.  If L1 wants to intercept #NM, then KVM must not inject the #NM
> and
> must not read XFD_ERR.

Sure. This v4 was sent out before we settled down this open in v3 
discussion. We did fix it later and posted the sample logic here:

https://lore.kernel.org/all/[e-mail]/

Will include this fix in v5.

Thanks
Kevin

Patch

diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h
index 6e5de2e2b0da..e325c290a816 100644
--- a/arch/x86/kvm/vmx/vmcs.h
+++ b/arch/x86/kvm/vmx/vmcs.h
@@ -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_fault(u32 intr_info)
+{
+	return is_exception_n(intr_info, NM_VECTOR);
+}
+
 /* Undocumented: icebp/int1 */
 static inline bool is_icebp(u32 intr_info)
 {
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 0dbf94eb954f..4e51de876085 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>
@@ -763,6 +764,13 @@  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);
 }
 
@@ -1960,6 +1968,12 @@  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))
@@ -4745,7 +4759,8 @@  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_fault(intr_info))
 		return 1; /* handled by handle_exception_nmi_irqoff() */
 
 	if (is_invalid_opcode(intr_info))
@@ -6349,6 +6364,12 @@  static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu,
 	kvm_after_interrupt(vcpu);
 }
 
+static void handle_nm_fault_irqoff(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;
@@ -6357,6 +6378,9 @@  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_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();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 36677b754ac9..b22defad5cab 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9893,6 +9893,9 @@  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);
@@ -9956,6 +9959,9 @@  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.