Avi,
A new VMX feature "Unrestricted Guest" feature is added in the VMX
specification. You can look at the latest Intel processor manual for
details of the feature here:
http://www.intel.com/products/processor/manuals
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@xxxxxxxxx>
Thanks & Regards,
Nitin
diff --git a/arch/x86/include/asm/kvm_host.h
b/arch/x86/include/asm/kvm_host.h
index d2b082d..7832599 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -40,9 +40,13 @@
#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_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST \
+ (X86_CR0_WP | X86_CR0_NE | X86_CR0_TS | X86_CR0_MP)
+#define KVM_VM_CR0_ALWAYS_ON_RESTRICTED_GUEST \
+ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
#define KVM_VM_CR0_ALWAYS_ON \
- (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
- | X86_CR0_MP)
+ (enable_unrestricted_guest ? KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST \
+ : KVM_VM_CR0_ALWAYS_ON_RESTRICTED_GUEST)
#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 498f944..c73da02 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 25f1239..703d2c4 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -50,6 +50,10 @@ module_param_named(flexpriority,
flexpriority_enabled, bool, S_IRUGO);
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);
@@ -268,6 +272,12 @@ static inline int cpu_has_vmx_ept(void)
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 &&
@@ -731,7 +741,7 @@ static unsigned long vmx_get_rflags(struct kvm_vcpu
*vcpu)
static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
- if (vcpu->arch.rmode.active)
+ if (vcpu->arch.rmode.active && !enable_unrestricted_guest)
rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
vmcs_writel(GUEST_RFLAGS, rflags);
}
@@ -1195,7 +1205,8 @@ static __init int setup_vmcs_config(struct
vmcs_config *vmcs_conf)
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)
@@ -1325,8 +1336,13 @@ static __init int hardware_setup(void)
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;
@@ -1363,9 +1379,17 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
unsigned long flags;
struct vcpu_vmx *vmx = to_vmx(vcpu);
- vmx->emulation_required = 1;
vcpu->arch.rmode.active = 0;
+ update_exception_bitmap(vcpu);
+
+ if (enable_unrestricted_guest) {
+ vmx->emulation_required = 0;
+ return;
+ }
+
+ vmx->emulation_required = 1;
+
vmcs_writel(GUEST_TR_BASE, vcpu->arch.rmode.tr.base);
vmcs_write32(GUEST_TR_LIMIT, vcpu->arch.rmode.tr.limit);
vmcs_write32(GUEST_TR_AR_BYTES, vcpu->arch.rmode.tr.ar);
@@ -1378,8 +1402,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
(vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME));
- update_exception_bitmap(vcpu);
-
if (emulate_invalid_guest_state)
return;
@@ -1425,8 +1447,15 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
unsigned long flags;
struct vcpu_vmx *vmx = to_vmx(vcpu);
- vmx->emulation_required = 1;
vcpu->arch.rmode.active = 1;
+ update_exception_bitmap(vcpu);
+
+ if (enable_unrestricted_guest) {
+ vmx->emulation_required = 0;
+ goto continue_rmode;
+ }
+
+ vmx->emulation_required = 1;
vcpu->arch.rmode.tr.base = vmcs_readl(GUEST_TR_BASE);
vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm));
@@ -1445,7 +1474,6 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
vmcs_writel(GUEST_RFLAGS, flags);
vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME);
- update_exception_bitmap(vcpu);
if (emulate_invalid_guest_state)
goto continue_rmode;
@@ -1563,7 +1591,6 @@ static void ept_update_paging_mode_cr0(unsigned
long *hw_cr0,
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 */
@@ -1733,6 +1760,23 @@ static u32 vmx_segment_access_rights(struct
kvm_segment *var)
return ar;
}
+static inline u32 get_segment_ar(int seg)
+{
+ if (!enable_unrestricted_guest)
+ return 0xf3;
+
+ switch (seg) {
+ case VCPU_SREG_CS:
+ return 0x9b;
+ case VCPU_SREG_TR:
+ return 0x8b;
+ case VCPU_SREG_LDTR:
+ return 0x82;
+ default:
+ return 0x93;
+ }
+}
+
static void vmx_set_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
@@ -1755,7 +1799,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
*/
if (var->base == 0xffff0000 && var->selector == 0xf000)
vmcs_writel(sf->base, 0xf0000);
- ar = 0xf3;
+ ar = get_segment_ar(seg);
} else
ar = vmx_segment_access_rights(var);
vmcs_write32(sf->ar_bytes, ar);
@@ -2058,7 +2102,7 @@ static void seg_setup(int seg)
vmcs_write16(sf->selector, 0);
vmcs_writel(sf->base, 0);
vmcs_write32(sf->limit, 0xffff);
- vmcs_write32(sf->ar_bytes, 0xf3);
+ vmcs_write32(sf->ar_bytes, get_segment_ar(seg));
}
static int alloc_apic_access_page(struct kvm *kvm)
@@ -2201,6 +2245,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
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);
}
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d2b082d..7832599 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -40,9 +40,13 @@
#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_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST \
+ (X86_CR0_WP | X86_CR0_NE | X86_CR0_TS | X86_CR0_MP)
+#define KVM_VM_CR0_ALWAYS_ON_RESTRICTED_GUEST \
+ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
#define KVM_VM_CR0_ALWAYS_ON \
- (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
- | X86_CR0_MP)
+ (enable_unrestricted_guest ? KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST \
+ : KVM_VM_CR0_ALWAYS_ON_RESTRICTED_GUEST)
#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 498f944..c73da02 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 25f1239..703d2c4 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -50,6 +50,10 @@ module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO);
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);
@@ -268,6 +272,12 @@ static inline int cpu_has_vmx_ept(void)
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 &&
@@ -731,7 +741,7 @@ static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
- if (vcpu->arch.rmode.active)
+ if (vcpu->arch.rmode.active && !enable_unrestricted_guest)
rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
vmcs_writel(GUEST_RFLAGS, rflags);
}
@@ -1195,7 +1205,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
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)
@@ -1325,8 +1336,13 @@ static __init int hardware_setup(void)
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;
@@ -1363,9 +1379,17 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
unsigned long flags;
struct vcpu_vmx *vmx = to_vmx(vcpu);
- vmx->emulation_required = 1;
vcpu->arch.rmode.active = 0;
+ update_exception_bitmap(vcpu);
+
+ if (enable_unrestricted_guest) {
+ vmx->emulation_required = 0;
+ return;
+ }
+
+ vmx->emulation_required = 1;
+
vmcs_writel(GUEST_TR_BASE, vcpu->arch.rmode.tr.base);
vmcs_write32(GUEST_TR_LIMIT, vcpu->arch.rmode.tr.limit);
vmcs_write32(GUEST_TR_AR_BYTES, vcpu->arch.rmode.tr.ar);
@@ -1378,8 +1402,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
(vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME));
- update_exception_bitmap(vcpu);
-
if (emulate_invalid_guest_state)
return;
@@ -1425,8 +1447,15 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
unsigned long flags;
struct vcpu_vmx *vmx = to_vmx(vcpu);
- vmx->emulation_required = 1;
vcpu->arch.rmode.active = 1;
+ update_exception_bitmap(vcpu);
+
+ if (enable_unrestricted_guest) {
+ vmx->emulation_required = 0;
+ goto continue_rmode;
+ }
+
+ vmx->emulation_required = 1;
vcpu->arch.rmode.tr.base = vmcs_readl(GUEST_TR_BASE);
vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm));
@@ -1445,7 +1474,6 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
vmcs_writel(GUEST_RFLAGS, flags);
vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME);
- update_exception_bitmap(vcpu);
if (emulate_invalid_guest_state)
goto continue_rmode;
@@ -1563,7 +1591,6 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
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 */
@@ -1733,6 +1760,23 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var)
return ar;
}
+static inline u32 get_segment_ar(int seg)
+{
+ if (!enable_unrestricted_guest)
+ return 0xf3;
+
+ switch (seg) {
+ case VCPU_SREG_CS:
+ return 0x9b;
+ case VCPU_SREG_TR:
+ return 0x8b;
+ case VCPU_SREG_LDTR:
+ return 0x82;
+ default:
+ return 0x93;
+ }
+}
+
static void vmx_set_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
@@ -1755,7 +1799,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
*/
if (var->base == 0xffff0000 && var->selector == 0xf000)
vmcs_writel(sf->base, 0xf0000);
- ar = 0xf3;
+ ar = get_segment_ar(seg);
} else
ar = vmx_segment_access_rights(var);
vmcs_write32(sf->ar_bytes, ar);
@@ -2058,7 +2102,7 @@ static void seg_setup(int seg)
vmcs_write16(sf->selector, 0);
vmcs_writel(sf->base, 0);
vmcs_write32(sf->limit, 0xffff);
- vmcs_write32(sf->ar_bytes, 0xf3);
+ vmcs_write32(sf->ar_bytes, get_segment_ar(seg));
}
static int alloc_apic_access_page(struct kvm *kvm)
@@ -2201,6 +2245,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
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);
}
