KVM: Use thread debug register storage instead of kvm specific data

Instead of saving the debug registers from the processor to a kvm data
structure, rely in the debug registers stored in the thread structure.
This allows us not to save dr6 and dr7.

Reduces lightweight vmexit cost by 350 cycles, or 11 percent.
Signed-off-by: Avi Kivity <avi@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -362,9 +362,6 @@ struct kvm_vcpu_arch {
 	u32 pat;
 
 	int switch_db_regs;
-	unsigned long host_db[KVM_NR_DB_REGS];
-	unsigned long host_dr6;
-	unsigned long host_dr7;
 	unsigned long db[KVM_NR_DB_REGS];
 	unsigned long dr6;
 	unsigned long dr7;

arch/x86/kvm/x86.c

@@ -3623,14 +3623,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	kvm_guest_enter();
 
-	get_debugreg(vcpu->arch.host_dr6, 6);
-	get_debugreg(vcpu->arch.host_dr7, 7);
 	if (unlikely(vcpu->arch.switch_db_regs)) {
-		get_debugreg(vcpu->arch.host_db[0], 0);
-		get_debugreg(vcpu->arch.host_db[1], 1);
-		get_debugreg(vcpu->arch.host_db[2], 2);
-		get_debugreg(vcpu->arch.host_db[3], 3);
-
 		set_debugreg(0, 7);
 		set_debugreg(vcpu->arch.eff_db[0], 0);
 		set_debugreg(vcpu->arch.eff_db[1], 1);
@@ -3641,15 +3634,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	trace_kvm_entry(vcpu->vcpu_id);
 	kvm_x86_ops->run(vcpu, kvm_run);
 
-	if (unlikely(vcpu->arch.switch_db_regs)) {
-		set_debugreg(0, 7);
-		set_debugreg(vcpu->arch.host_db[0], 0);
-		set_debugreg(vcpu->arch.host_db[1], 1);
-		set_debugreg(vcpu->arch.host_db[2], 2);
-		set_debugreg(vcpu->arch.host_db[3], 3);
+	if (unlikely(vcpu->arch.switch_db_regs || test_thread_flag(TIF_DEBUG))) {
+		set_debugreg(current->thread.debugreg0, 0);
+		set_debugreg(current->thread.debugreg1, 1);
+		set_debugreg(current->thread.debugreg2, 2);
+		set_debugreg(current->thread.debugreg3, 3);
+		set_debugreg(current->thread.debugreg6, 6);
+		set_debugreg(current->thread.debugreg7, 7);
 	}
-	set_debugreg(vcpu->arch.host_dr6, 6);
-	set_debugreg(vcpu->arch.host_dr7, 7);
 
 	set_bit(KVM_REQ_KICK, &vcpu->requests);
 	local_irq_enable();