KVM: VMX: Support Unrestricted Guest feature
"Unrestricted Guest" feature is added in the VMX specification.
Intel Westmere and onwards processors will support this feature.
It allows kvm guests to run real mode and unpaged mode
code natively in the VMX mode when EPT is turned on. With the
unrestricted guest there is no need to emulate the guest real mode code
in the vm86 container or in the emulator. Also the guest big real mode
code works like native.
The attached patch enhances KVM to use the unrestricted guest feature
if available on the processor. It also adds a new kernel/module
parameter to disable the unrestricted guest feature at the boot time.
Signed-off-by: Nitin A Kamble <nitin.a.kamble@intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1cc901e..a1a96a5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -37,12 +37,14 @@
#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS | \
0xFFFFFF0000000000ULL)
-#define KVM_GUEST_CR0_MASK \
- (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE \
- | X86_CR0_NW | X86_CR0_CD)
+#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST \
+ (X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD)
+#define KVM_GUEST_CR0_MASK \
+ (KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
+#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST \
+ (X86_CR0_WP | X86_CR0_NE | X86_CR0_TS | X86_CR0_MP)
#define KVM_VM_CR0_ALWAYS_ON \
- (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
- | X86_CR0_MP)
+ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
#define KVM_GUEST_CR4_MASK \
(X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE)
#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 11be5ad..e7927a6 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -55,6 +55,7 @@
#define SECONDARY_EXEC_ENABLE_EPT 0x00000002
#define SECONDARY_EXEC_ENABLE_VPID 0x00000020
#define SECONDARY_EXEC_WBINVD_EXITING 0x00000040
+#define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080
#define PIN_BASED_EXT_INTR_MASK 0x00000001
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 959cb59..f0f9773 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -51,6 +51,10 @@
static int __read_mostly enable_ept = 1;
module_param_named(ept, enable_ept, bool, S_IRUGO);
+static int __read_mostly enable_unrestricted_guest = 1;
+module_param_named(unrestricted_guest,
+ enable_unrestricted_guest, bool, S_IRUGO);
+
static int __read_mostly emulate_invalid_guest_state = 0;
module_param(emulate_invalid_guest_state, bool, S_IRUGO);
@@ -279,6 +283,12 @@
SECONDARY_EXEC_ENABLE_EPT;
}
+static inline int cpu_has_vmx_unrestricted_guest(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_UNRESTRICTED_GUEST;
+}
+
static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
{
return flexpriority_enabled &&
@@ -1210,7 +1220,8 @@
opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
SECONDARY_EXEC_WBINVD_EXITING |
SECONDARY_EXEC_ENABLE_VPID |
- SECONDARY_EXEC_ENABLE_EPT;
+ SECONDARY_EXEC_ENABLE_EPT |
+ SECONDARY_EXEC_UNRESTRICTED_GUEST;
if (adjust_vmx_controls(min2, opt2,
MSR_IA32_VMX_PROCBASED_CTLS2,
&_cpu_based_2nd_exec_control) < 0)
@@ -1340,8 +1351,13 @@
if (!cpu_has_vmx_vpid())
enable_vpid = 0;
- if (!cpu_has_vmx_ept())
+ if (!cpu_has_vmx_ept()) {
enable_ept = 0;
+ enable_unrestricted_guest = 0;
+ }
+
+ if (!cpu_has_vmx_unrestricted_guest())
+ enable_unrestricted_guest = 0;
if (!cpu_has_vmx_flexpriority())
flexpriority_enabled = 0;
@@ -1440,6 +1456,9 @@
unsigned long flags;
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ if (enable_unrestricted_guest)
+ return;
+
vmx->emulation_required = 1;
vcpu->arch.rmode.vm86_active = 1;
@@ -1593,7 +1612,6 @@
CPU_BASED_CR3_STORE_EXITING));
vcpu->arch.cr0 = cr0;
vmx_set_cr4(vcpu, vcpu->arch.cr4);
- *hw_cr0 |= X86_CR0_PE | X86_CR0_PG;
*hw_cr0 &= ~X86_CR0_WP;
} else if (!is_paging(vcpu)) {
/* From nonpaging to paging */
@@ -1620,8 +1638,13 @@
static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
- unsigned long hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) |
- KVM_VM_CR0_ALWAYS_ON;
+ unsigned long hw_cr0;
+
+ if (enable_unrestricted_guest)
+ hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST)
+ | KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
+ else
+ hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON;
vmx_fpu_deactivate(vcpu);
@@ -1786,6 +1809,21 @@
ar = 0xf3;
} else
ar = vmx_segment_access_rights(var);
+
+ /*
+ * Fix the "Accessed" bit in AR field of segment registers for older
+ * qemu binaries.
+ * IA32 arch specifies that at the time of processor reset the
+ * "Accessed" bit in the AR field of segment registers is 1. And qemu
+ * is setting it to 0 in the usedland code. This causes invalid guest
+ * state vmexit when "unrestricted guest" mode is turned on.
+ * Fix for this setup issue in cpu_reset is being pushed in the qemu
+ * tree. Newer qemu binaries with that qemu fix would not need this
+ * kvm hack.
+ */
+ if (enable_unrestricted_guest && (seg != VCPU_SREG_LDTR))
+ ar |= 0x1; /* Accessed */
+
vmcs_write32(sf->ar_bytes, ar);
}
@@ -2082,11 +2120,19 @@
static void seg_setup(int seg)
{
struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+ unsigned int ar;
vmcs_write16(sf->selector, 0);
vmcs_writel(sf->base, 0);
vmcs_write32(sf->limit, 0xffff);
- vmcs_write32(sf->ar_bytes, 0xf3);
+ if (enable_unrestricted_guest) {
+ ar = 0x93;
+ if (seg == VCPU_SREG_CS)
+ ar |= 0x08; /* code segment */
+ } else
+ ar = 0xf3;
+
+ vmcs_write32(sf->ar_bytes, ar);
}
static int alloc_apic_access_page(struct kvm *kvm)
@@ -2229,6 +2275,8 @@
exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
if (!enable_ept)
exec_control &= ~SECONDARY_EXEC_ENABLE_EPT;
+ if (!enable_unrestricted_guest)
+ exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
}