[PATCH v3 22/22] kvm: x86: Disable interception for IA32_XFD on demand

[Jing Liu]

Always intercepting IA32_XFD causes non-negligible overhead when this
register is updated frequently in the guest.

Disable r/w emulation after intercepting the first WRMSR(IA32_XFD)
with a non-zero value.

Disable WRMSR emulation implies that IA32_XFD becomes out-of-sync
with the software states in fpstate and the per-cpu xfd cache. Call
fpu_sync_guest_vmexit_xfd_state() to bring them back in-sync, before
preemption is enabled.

p.s. We have confirmed that SDM is being revised to say that
when setting IA32_XFD[18] the AMX register state is not guaranteed
to be preserved. This clarification avoids adding mess for a creative
guest which sets IA32_XFD[18]=1 before saving active AMX state to
its own storage.

Signed-off-by: Kevin Tian <kevin.tian@xxxxxxxxx>
Signed-off-by: Yang Zhong <yang.zhong@xxxxxxxxx>
Signed-off-by: Jing Liu <jing2.liu@xxxxxxxxx>
---
 arch/x86/include/asm/kvm_host.h | 1 +
 arch/x86/kvm/vmx/vmx.c          | 4 ++++
 arch/x86/kvm/vmx/vmx.h          | 2 +-
 arch/x86/kvm/x86.c              | 3 +++
 4 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f7a661f35d1a..7b81d324b32a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -641,6 +641,7 @@ struct kvm_vcpu_arch {
 	bool tpr_access_reporting;
 	bool xsaves_enabled;
 	bool trap_nm;
+	bool xfd_out_of_sync;
 	u64 ia32_xss;
 	u64 microcode_version;
 	u64 arch_capabilities;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 8595a3e8fbd8..7aaf905e13b4 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -162,6 +162,7 @@ static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = {
 	MSR_FS_BASE,
 	MSR_GS_BASE,
 	MSR_KERNEL_GS_BASE,
+	MSR_IA32_XFD,
 	MSR_IA32_XFD_ERR,
 #endif
 	MSR_IA32_SYSENTER_CS,
@@ -1968,6 +1969,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_XFD:
 		ret = kvm_set_msr_common(vcpu, msr_info);
 		if (!ret && data) {
+			vmx_disable_intercept_for_msr(vcpu, MSR_IA32_XFD, MSR_TYPE_RW);
+			vcpu->arch.xfd_out_of_sync = true;
+
 			vcpu->arch.trap_nm = true;
 			vmx_update_exception_bitmap(vcpu);
 		}
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index bf9d3051cd6c..0a00242a91e7 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -340,7 +340,7 @@ struct vcpu_vmx {
 	struct lbr_desc lbr_desc;
 
 	/* Save desired MSR intercept (read: pass-through) state */
-#define MAX_POSSIBLE_PASSTHROUGH_MSRS	14
+#define MAX_POSSIBLE_PASSTHROUGH_MSRS	15
 	struct {
 		DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
 		DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3b756ff13103..10a08aa2aa45 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10024,6 +10024,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.guest_fpu.xfd_err)
 		wrmsrl(MSR_IA32_XFD_ERR, 0);
 
+	if (vcpu->arch.xfd_out_of_sync)
+		fpu_sync_guest_vmexit_xfd_state();
+
 	/*
 	 * Consume any pending interrupts, including the possible source of
 	 * VM-Exit on SVM and any ticks that occur between VM-Exit and now.
-- 
2.27.0