[PATCH v2] KVM: VMX: Cache IA32_DEBUGCTL in memory

[Wanpeng Li]

From: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>

MSR_IA32_DEBUGCTLMSR is zeroed on VMEXIT, so it is saved/restored 
each time during world switch. Jim from Google pointed out that 
when running schbench in L2, vmx_vcpu_run will occupy 4% cpu time, 
and the 25% of vmx_vcpu_run cpu time is occupied by get_debugctlmsr(). 
This patch caches the host IA32_DEBUGCTL MSR and saves/restores 
the host IA32_DEBUGCTL msr when guest/host switches to avoid to 
save/restore each time during world switch.

Suggested-by: Jim Mattson <jmattson@xxxxxxxxxx>
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
Cc: Jim Mattson <jmattson@xxxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
---
v1 ->  v2:
 * rename to host_debugctlmsr and place it in struct vcpu_struct
 * update_debugctlmsr stay in vmx_vcpu_run

 arch/x86/kvm/vmx.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 8c7e816..d293c29 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -658,6 +658,8 @@ struct vcpu_vmx {
 
 	u32 host_pkru;
 
+	unsigned long host_debugctlmsr;
+
 	/*
 	 * Only bits masked by msr_ia32_feature_control_valid_bits can be set in
 	 * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included
@@ -2326,6 +2328,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	vmx_vcpu_pi_load(vcpu, cpu);
 	vmx->host_pkru = read_pkru();
+	vmx->host_debugctlmsr = get_debugctlmsr();
 }
 
 static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
@@ -9346,7 +9349,7 @@ static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
 static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long debugctlmsr, cr3, cr4;
+	unsigned long cr3, cr4;
 
 	/* Record the guest's net vcpu time for enforced NMI injections. */
 	if (unlikely(!enable_vnmi &&
@@ -9399,7 +9402,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		__write_pkru(vcpu->arch.pkru);
 
 	atomic_switch_perf_msrs(vmx);
-	debugctlmsr = get_debugctlmsr();
 
 	vmx_arm_hv_timer(vcpu);
 
@@ -9510,8 +9512,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	      );
 
 	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
-	if (debugctlmsr)
-		update_debugctlmsr(debugctlmsr);
+	if (vmx->host_debugctlmsr)
+		update_debugctlmsr(vmx->host_debugctlmsr);
 
 #ifndef CONFIG_X86_64
 	/*
-- 
2.7.4