KVM: VMX: don't force CR4.PAE/PSE for unrestricted guest

CR4.PAE - Unrestricted guest can only be enabled when EPT is
enabled, and vmx_set_cr4() clears hardware CR0.PAE based on
the guest's CR4.PAE, i.e. CR4.PAE always follows the guest's
value when unrestricted guest is enabled.

CR4.PSE - Unrestricted guest no longer uses the identity mapped
IA32 page tables since CR0.PG can be cleared in hardware, thus
there is no need to set CR4.PSE when paging is disabled in the
guest (and EPT is enabled).

Define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST (to X86_CR4_VMXE)
and use it in lieu of KVM_*MODE_VM_CR4_ALWAYS_ON when unrestricted
guest is enabled, which removes the forcing of CR4.PAE.

Skip the manipulation of CR4.PAE/PSE for EPT when unrestricted
guest is enabled, as CR4.PAE isn't forced and so doesn't need to
be manually cleared, and CR4.PSE does not need to be set when
paging is disabled since the identity mapped IA32 page tables
are not used.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 8e7f209c1d2731eb7d858395a21c527b1fbb664f..d35e5c643091dbfab2deb866ab6bfebf3cfc4f3c 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -139,6 +139,7 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
        (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR      \
         | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD)
 
+#define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE
 #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
 #define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
 
@@ -4510,11 +4511,15 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
         * is in force while we are in guest mode.  Do not let guests control
         * this bit, even if host CR4.MCE == 0.
         */
-       unsigned long hw_cr4 =
-               (cr4_read_shadow() & X86_CR4_MCE) |
-               (cr4 & ~X86_CR4_MCE) |
-               (to_vmx(vcpu)->rmode.vm86_active ?
-                KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
+       unsigned long hw_cr4;
+
+       hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE);
+       if (enable_unrestricted_guest)
+               hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST;
+       else if (to_vmx(vcpu)->rmode.vm86_active)
+               hw_cr4 |= KVM_RMODE_VM_CR4_ALWAYS_ON;
+       else
+               hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON;
 
        if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) {
                vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
@@ -4540,16 +4545,17 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
                return 1;
 
        vcpu->arch.cr4 = cr4;
-       if (enable_ept) {
-               if (!is_paging(vcpu)) {
-                       hw_cr4 &= ~X86_CR4_PAE;
-                       hw_cr4 |= X86_CR4_PSE;
-               } else if (!(cr4 & X86_CR4_PAE)) {
-                       hw_cr4 &= ~X86_CR4_PAE;
+
+       if (!enable_unrestricted_guest) {
+               if (enable_ept) {
+                       if (!is_paging(vcpu)) {
+                               hw_cr4 &= ~X86_CR4_PAE;
+                               hw_cr4 |= X86_CR4_PSE;
+                       } else if (!(cr4 & X86_CR4_PAE)) {
+                               hw_cr4 &= ~X86_CR4_PAE;
+                       }
                }
-       }
 
-       if (!enable_unrestricted_guest && !is_paging(vcpu))
                /*
                 * SMEP/SMAP/PKU is disabled if CPU is in non-paging mode in
                 * hardware.  To emulate this behavior, SMEP/SMAP/PKU needs
@@ -4561,7 +4567,9 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
                 * If enable_unrestricted_guest, the CPU automatically
                 * disables SMEP/SMAP/PKU when the guest sets CR0.PG=0.
                 */
-               hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE);
+               if (!is_paging(vcpu))
+                       hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE);
+       }
 
        vmcs_writel(CR4_READ_SHADOW, cr4);
        vmcs_writel(GUEST_CR4, hw_cr4);