[PATCH 24/29] nVMX: Handling of CR0 and CR4 modifying instructions

["Nadav Har'El" <nyh@il.ibm.com>]

When L2 tries to modify CR0 or CR4 (with mov or clts), and modifies a bit
which L1 asked to shadow (via CR[04]_GUEST_HOST_MASK), we already do the right
thing: we let L1 handle the trap (see nested_vmx_exit_handled_cr() in a
previous patch).
When L2 modifies bits that L1 doesn't care about, we let it think (via
CR[04]_READ_SHADOW) that it did these modifications, while only changing
(in GUEST_CR[04]) the bits that L0 doesn't shadow.

This is needed for corect handling of CR0.TS for lazy FPU loading: L0 may
want to leave TS on, while pretending to allow the guest to change it.

Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
---
 arch/x86/kvm/vmx.c |   53 ++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 50 insertions(+), 3 deletions(-)

--- .before/arch/x86/kvm/vmx.c	2011-01-26 18:06:06.000000000 +0200
+++ .after/arch/x86/kvm/vmx.c	2011-01-26 18:06:06.000000000 +0200
@@ -3872,6 +3872,53 @@ vmx_patch_hypercall(struct kvm_vcpu *vcp
 	hypercall[2] = 0xc1;
 }
 
+/* called to set cr0 as approriate for a mov-to-cr0 exit. */
+static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	if (is_guest_mode(vcpu)) {
+		/*
+		 * We get here when L2 changed cr0 in a way that did not change
+		 * any of L1's shadowed bits (see nested_vmx_exit_handled_cr),
+		 * but did change L0 shadowed bits. This can currently happen
+		 * with the TS bit: L0 may want to leave TS on (for lazy fpu
+		 * loading) while pretending to allow the guest to change it.
+		 */
+		vmcs_writel(GUEST_CR0,
+		   (val & vcpu->arch.cr0_guest_owned_bits) |
+		   (vmcs_readl(GUEST_CR0) & ~vcpu->arch.cr0_guest_owned_bits));
+		vmcs_writel(CR0_READ_SHADOW, val);
+		vcpu->arch.cr0 = val;
+		return 0;
+	} else
+		return kvm_set_cr0(vcpu, val);
+}
+
+static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	if (is_guest_mode(vcpu)) {
+		vmcs_writel(GUEST_CR4,
+		   (val & vcpu->arch.cr4_guest_owned_bits) |
+		   (vmcs_readl(GUEST_CR4) & ~vcpu->arch.cr4_guest_owned_bits));
+		vmcs_writel(CR4_READ_SHADOW, val);
+		vcpu->arch.cr4 = val;
+		return 0;
+	} else
+		return kvm_set_cr4(vcpu, val);
+}
+
+/* called to set cr0 as approriate for clts instruction exit. */
+static void handle_clts(struct kvm_vcpu *vcpu)
+{
+	if (is_guest_mode(vcpu)) {
+		/* As in handle_set_cr0(), we can't call vmx_set_cr0 here */
+		vmcs_writel(GUEST_CR0, vmcs_readl(GUEST_CR0) & ~X86_CR0_TS);
+		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;
@@ -3888,7 +3935,7 @@ static int handle_cr(struct kvm_vcpu *vc
 		trace_kvm_cr_write(cr, val);
 		switch (cr) {
 		case 0:
-			err = kvm_set_cr0(vcpu, val);
+			err = handle_set_cr0(vcpu, val);
 			kvm_complete_insn_gp(vcpu, err);
 			return 1;
 		case 3:
@@ -3896,7 +3943,7 @@ static int handle_cr(struct kvm_vcpu *vc
 			kvm_complete_insn_gp(vcpu, err);
 			return 1;
 		case 4:
-			err = kvm_set_cr4(vcpu, val);
+			err = handle_set_cr4(vcpu, val);
 			kvm_complete_insn_gp(vcpu, err);
 			return 1;
 		case 8: {
@@ -3914,7 +3961,7 @@ static int handle_cr(struct kvm_vcpu *vc
 		};
 		break;
 	case 2: /* clts */
-		vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
+		handle_clts(vcpu);
 		trace_kvm_cr_write(0, kvm_read_cr0(vcpu));
 		skip_emulated_instruction(vcpu);
 		vmx_fpu_activate(vcpu);