KVM: x86: remove code for lazy FPU handling

The FPU is always active now when running KVM.

Reviewed-by: David Matlack <dmatlack@google.com>
Reviewed-by: Bandan Das <bsd@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 0e0b5d0..9856b73 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1856,7 +1856,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	u32 eb;
 
 	eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |
-	     (1u << NM_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR);
+	     (1u << DB_VECTOR) | (1u << AC_VECTOR);
 	if ((vcpu->guest_debug &
 	     (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) ==
 	    (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP))
@@ -1865,8 +1865,6 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 		eb = ~0;
 	if (enable_ept)
 		eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */
-	if (vcpu->fpu_active)
-		eb &= ~(1u << NM_VECTOR);
 
 	/* When we are running a nested L2 guest and L1 specified for it a
 	 * certain exception bitmap, we must trap the same exceptions and pass
@@ -2340,25 +2338,6 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void vmx_fpu_activate(struct kvm_vcpu *vcpu)
-{
-	ulong cr0;
-
-	if (vcpu->fpu_active)
-		return;
-	vcpu->fpu_active = 1;
-	cr0 = vmcs_readl(GUEST_CR0);
-	cr0 &= ~(X86_CR0_TS | X86_CR0_MP);
-	cr0 |= kvm_read_cr0_bits(vcpu, X86_CR0_TS | X86_CR0_MP);
-	vmcs_writel(GUEST_CR0, cr0);
-	update_exception_bitmap(vcpu);
-	vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
-	if (is_guest_mode(vcpu))
-		vcpu->arch.cr0_guest_owned_bits &=
-			~get_vmcs12(vcpu)->cr0_guest_host_mask;
-	vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
-}
-
 static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu);
 
 /*
@@ -2377,33 +2356,6 @@ static inline unsigned long nested_read_cr4(struct vmcs12 *fields)
 		(fields->cr4_read_shadow & fields->cr4_guest_host_mask);
 }
 
-static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu)
-{
-	/* Note that there is no vcpu->fpu_active = 0 here. The caller must
-	 * set this *before* calling this function.
-	 */
-	vmx_decache_cr0_guest_bits(vcpu);
-	vmcs_set_bits(GUEST_CR0, X86_CR0_TS | X86_CR0_MP);
-	update_exception_bitmap(vcpu);
-	vcpu->arch.cr0_guest_owned_bits = 0;
-	vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
-	if (is_guest_mode(vcpu)) {
-		/*
-		 * L1's specified read shadow might not contain the TS bit,
-		 * so now that we turned on shadowing of this bit, we need to
-		 * set this bit of the shadow. Like in nested_vmx_run we need
-		 * nested_read_cr0(vmcs12), but vmcs12->guest_cr0 is not yet
-		 * up-to-date here because we just decached cr0.TS (and we'll
-		 * only update vmcs12->guest_cr0 on nested exit).
-		 */
-		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-		vmcs12->guest_cr0 = (vmcs12->guest_cr0 & ~X86_CR0_TS) |
-			(vcpu->arch.cr0 & X86_CR0_TS);
-		vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12));
-	} else
-		vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
-}
-
 static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
 {
 	unsigned long rflags, save_rflags;
@@ -4232,9 +4184,6 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	if (enable_ept)
 		ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu);
 
-	if (!vcpu->fpu_active)
-		hw_cr0 |= X86_CR0_TS | X86_CR0_MP;
-
 	vmcs_writel(CR0_READ_SHADOW, cr0);
 	vmcs_writel(GUEST_CR0, hw_cr0);
 	vcpu->arch.cr0 = cr0;
@@ -5321,7 +5270,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	/* 22.2.1, 20.8.1 */
 	vm_entry_controls_init(vmx, vmcs_config.vmentry_ctrl);
 
-	vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
+	vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS;
+	vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS);
+
 	set_cr4_guest_host_mask(vmx);
 
 	if (vmx_xsaves_supported())
@@ -5425,7 +5376,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vmx_set_cr0(vcpu, cr0); /* enter rmode */
 	vmx_set_cr4(vcpu, 0);
 	vmx_set_efer(vcpu, 0);
-	vmx_fpu_activate(vcpu);
+
 	update_exception_bitmap(vcpu);
 
 	vpid_sync_context(vmx->vpid);
@@ -5698,11 +5649,6 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 	if (is_nmi(intr_info))
 		return 1;  /* already handled by vmx_vcpu_run() */
 
-	if (is_no_device(intr_info)) {
-		vmx_fpu_activate(vcpu);
-		return 1;
-	}
-
 	if (is_invalid_opcode(intr_info)) {
 		if (is_guest_mode(vcpu)) {
 			kvm_queue_exception(vcpu, UD_VECTOR);
@@ -5892,22 +5838,6 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val)
 		return kvm_set_cr4(vcpu, val);
 }
 
-/* called to set cr0 as appropriate for clts instruction exit. */
-static void handle_clts(struct kvm_vcpu *vcpu)
-{
-	if (is_guest_mode(vcpu)) {
-		/*
-		 * We get here when L2 did CLTS, and L1 didn't shadow CR0.TS
-		 * but we did (!fpu_active). We need to keep GUEST_CR0.TS on,
-		 * just pretend it's off (also in arch.cr0 for fpu_activate).
-		 */
-		vmcs_writel(CR0_READ_SHADOW,
-			vmcs_readl(CR0_READ_SHADOW) & ~X86_CR0_TS);
-		vcpu->arch.cr0 &= ~X86_CR0_TS;
-	} else
-		vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
-}
-
 static int handle_cr(struct kvm_vcpu *vcpu)
 {
 	unsigned long exit_qualification, val;
@@ -5953,9 +5883,9 @@ static int handle_cr(struct kvm_vcpu *vcpu)
 		}
 		break;
 	case 2: /* clts */
-		handle_clts(vcpu);
+		WARN_ONCE(1, "Guest should always own CR0.TS");
+		vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
 		trace_kvm_cr_write(0, kvm_read_cr0(vcpu));
-		vmx_fpu_activate(vcpu);
 		return kvm_skip_emulated_instruction(vcpu);
 	case 1: /*mov from cr*/
 		switch (cr) {
@@ -10349,8 +10279,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	}
 
 	/*
-	 * This sets GUEST_CR0 to vmcs12->guest_cr0, with possibly a modified
-	 * TS bit (for lazy fpu) and bits which we consider mandatory enabled.
+	 * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those
+	 * bits which we consider mandatory enabled.
 	 * The CR0_READ_SHADOW is what L2 should have expected to read given
 	 * the specifications by L1; It's not enough to take
 	 * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we we
@@ -10963,24 +10893,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vmx_set_rflags(vcpu, X86_EFLAGS_FIXED);
 	/*
 	 * Note that calling vmx_set_cr0 is important, even if cr0 hasn't
-	 * actually changed, because it depends on the current state of
-	 * fpu_active (which may have changed).
-	 * Note that vmx_set_cr0 refers to efer set above.
+	 * actually changed, because vmx_set_cr0 refers to efer set above.
+	 *
+	 * CR0_GUEST_HOST_MASK is already set in the original vmcs01
+	 * (KVM doesn't change it);
 	 */
+	vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
 	vmx_set_cr0(vcpu, vmcs12->host_cr0);
-	/*
-	 * If we did fpu_activate()/fpu_deactivate() during L2's run, we need
-	 * to apply the same changes to L1's vmcs. We just set cr0 correctly,
-	 * but we also need to update cr0_guest_host_mask and exception_bitmap.
-	 */
-	update_exception_bitmap(vcpu);
-	vcpu->arch.cr0_guest_owned_bits = (vcpu->fpu_active ? X86_CR0_TS : 0);
-	vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
 
-	/*
-	 * Note that CR4_GUEST_HOST_MASK is already set in the original vmcs01
-	 * (KVM doesn't change it)- no reason to call set_cr4_guest_host_mask();
-	 */
+	/* Same as above - no reason to call set_cr4_guest_host_mask().  */
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
 	kvm_set_cr4(vcpu, vmcs12->host_cr4);
 
@@ -11609,9 +11530,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 
 	.get_pkru = vmx_get_pkru,
 
-	.fpu_activate = vmx_fpu_activate,
-	.fpu_deactivate = vmx_fpu_deactivate,
-
 	.tlb_flush = vmx_flush_tlb,
 
 	.run = vmx_vcpu_run,