[PATCH v3 2/5] KVM: nVMX: support restore of VMX capability MSRs

[David Matlack]

The VMX capability MSRs advertise the set of features the KVM virtual
CPU can support. This set of features varies across different host CPUs
and KVM versions. This patch aims to addresses both sources of
differences, allowing VMs to be migrated across CPUs and KVM versions
without guest-visible changes to these MSRs. Note that cross-KVM-
version migration is only supported from this point forward.

When the VMX capability MSRs are restored, they are audited to check
that the set of features advertised are a subset of what KVM and the
CPU support.

Since the VMX capability MSRs are read-only, they do not need to be on
the default MSR save/restore lists. The userspace hypervisor can set
the values of these MSRs or read them from KVM at VCPU creation time,
and restore the same value after every save/restore.

Signed-off-by: David Matlack <dmatlack@xxxxxxxxxx>
---
 arch/x86/include/asm/vmx.h |  31 +++++
 arch/x86/kvm/vmx.c         | 290 +++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 297 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index a002b07..a4ca897 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -25,6 +25,7 @@
 #define VMX_H
 
 
+#include <linux/bitops.h>
 #include <linux/types.h>
 #include <uapi/asm/vmx.h>
 
@@ -110,6 +111,36 @@
 #define VMX_MISC_SAVE_EFER_LMA			0x00000020
 #define VMX_MISC_ACTIVITY_HLT			0x00000040
 
+static inline u32 vmx_basic_vmcs_revision_id(u64 vmx_basic)
+{
+	return vmx_basic & GENMASK_ULL(30, 0);
+}
+
+static inline u32 vmx_basic_vmcs_size(u64 vmx_basic)
+{
+	return (vmx_basic & GENMASK_ULL(44, 32)) >> 32;
+}
+
+static inline int vmx_misc_preemption_timer_rate(u64 vmx_misc)
+{
+	return vmx_misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
+}
+
+static inline int vmx_misc_cr3_count(u64 vmx_misc)
+{
+	return (vmx_misc & GENMASK_ULL(24, 16)) >> 16;
+}
+
+static inline int vmx_misc_max_msr(u64 vmx_misc)
+{
+	return (vmx_misc & GENMASK_ULL(27, 25)) >> 25;
+}
+
+static inline int vmx_misc_mseg_revid(u64 vmx_misc)
+{
+	return (vmx_misc & GENMASK_ULL(63, 32)) >> 32;
+}
+
 /* VMCS Encodings */
 enum vmcs_field {
 	VIRTUAL_PROCESSOR_ID            = 0x00000000,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 0beb56a..01a2b9e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -465,6 +465,12 @@ struct nested_vmx {
 	u32 nested_vmx_misc_high;
 	u32 nested_vmx_ept_caps;
 	u32 nested_vmx_vpid_caps;
+	u64 nested_vmx_basic;
+	u64 nested_vmx_cr0_fixed0;
+	u64 nested_vmx_cr0_fixed1;
+	u64 nested_vmx_cr4_fixed0;
+	u64 nested_vmx_cr4_fixed1;
+	u64 nested_vmx_vmcs_enum;
 };
 
 #define POSTED_INTR_ON  0
@@ -2826,6 +2832,36 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
 		VMX_MISC_ACTIVITY_HLT;
 	vmx->nested.nested_vmx_misc_high = 0;
+
+	/*
+	 * This MSR reports some information about VMX support. We
+	 * should return information about the VMX we emulate for the
+	 * guest, and the VMCS structure we give it - not about the
+	 * VMX support of the underlying hardware.
+	 */
+	vmx->nested.nested_vmx_basic =
+		VMCS12_REVISION |
+		VMX_BASIC_TRUE_CTLS |
+		((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) |
+		(VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT);
+
+	if (cpu_has_vmx_basic_inout())
+		vmx->nested.nested_vmx_basic |= VMX_BASIC_INOUT;
+
+	/*
+	 * These MSRs specify bits which the guest must keep fixed (on or off)
+	 * while L1 is in VMXON mode (in L1's root mode, or running an L2).
+	 * We picked the standard core2 setting.
+	 */
+#define VMXON_CR0_ALWAYSON     (X86_CR0_PE | X86_CR0_PG | X86_CR0_NE)
+#define VMXON_CR4_ALWAYSON     X86_CR4_VMXE
+	vmx->nested.nested_vmx_cr0_fixed0 = VMXON_CR0_ALWAYSON;
+	vmx->nested.nested_vmx_cr0_fixed1 = -1ULL;
+	vmx->nested.nested_vmx_cr4_fixed0 = VMXON_CR4_ALWAYSON;
+	vmx->nested.nested_vmx_cr4_fixed1 = -1ULL;
+
+	/* highest index: VMX_PREEMPTION_TIMER_VALUE */
+	vmx->nested.nested_vmx_vmcs_enum = 0x2e;
 }
 
 static inline bool vmx_control_verify(u32 control, u32 low, u32 high)
@@ -2841,24 +2877,233 @@ static inline u64 vmx_control_msr(u32 low, u32 high)
 	return low | ((u64)high << 32);
 }
 
-/* Returns 0 on success, non-0 otherwise. */
-static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
+static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
+{
+	superset &= mask;
+	subset &= mask;
+
+	return (superset | subset) == superset;
+}
+
+static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data)
+{
+	const u64 feature_and_reserved =
+		/* feature (except bit 48; see below) */
+		BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) |
+		/* reserved */
+		BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56);
+	u64 vmx_basic = vmx->nested.nested_vmx_basic;
+
+	if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved))
+		return -EINVAL;
+
+	/*
+	 * KVM does not emulate a version of VMX that constrains physical
+	 * addresses of VMX structures (e.g. VMCS) to 32-bits.
+	 */
+	if (data & BIT_ULL(48))
+		return -EINVAL;
+
+	if (vmx_basic_vmcs_revision_id(vmx_basic) !=
+	    vmx_basic_vmcs_revision_id(data))
+		return -EINVAL;
+
+	if (vmx_basic_vmcs_size(vmx_basic) > vmx_basic_vmcs_size(data))
+		return -EINVAL;
+
+	vmx->nested.nested_vmx_basic = data;
+	return 0;
+}
+
+static int
+vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
+{
+	u64 supported;
+	u32 *lowp, *highp;
+
+	switch (msr_index) {
+	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
+		lowp = &vmx->nested.nested_vmx_pinbased_ctls_low;
+		highp = &vmx->nested.nested_vmx_pinbased_ctls_high;
+		break;
+	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
+		lowp = &vmx->nested.nested_vmx_procbased_ctls_low;
+		highp = &vmx->nested.nested_vmx_procbased_ctls_high;
+		break;
+	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
+		lowp = &vmx->nested.nested_vmx_exit_ctls_low;
+		highp = &vmx->nested.nested_vmx_exit_ctls_high;
+		break;
+	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
+		lowp = &vmx->nested.nested_vmx_entry_ctls_low;
+		highp = &vmx->nested.nested_vmx_entry_ctls_high;
+		break;
+	case MSR_IA32_VMX_PROCBASED_CTLS2:
+		lowp = &vmx->nested.nested_vmx_secondary_ctls_low;
+		highp = &vmx->nested.nested_vmx_secondary_ctls_high;
+		break;
+	default:
+		BUG();
+	}
+
+	supported = vmx_control_msr(*lowp, *highp);
+
+	/* Check must-be-1 bits are still 1. */
+	if (!is_bitwise_subset(data, supported, GENMASK_ULL(31, 0)))
+		return -EINVAL;
+
+	/* Check must-be-0 bits are still 0. */
+	if (!is_bitwise_subset(supported, data, GENMASK_ULL(63, 32)))
+		return -EINVAL;
+
+	*lowp = data;
+	*highp = data >> 32;
+	return 0;
+}
+
+static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data)
+{
+	const u64 feature_and_reserved_bits =
+		/* feature */
+		BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) |
+		BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) |
+		/* reserved */
+		GENMASK_ULL(13, 9) | BIT_ULL(31);
+	u64 vmx_misc;
+
+	vmx_misc = vmx_control_msr(vmx->nested.nested_vmx_misc_low,
+				   vmx->nested.nested_vmx_misc_high);
+
+	if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits))
+		return -EINVAL;
+
+	if ((vmx->nested.nested_vmx_pinbased_ctls_high &
+	     PIN_BASED_VMX_PREEMPTION_TIMER) &&
+	    vmx_misc_preemption_timer_rate(data) !=
+	    vmx_misc_preemption_timer_rate(vmx_misc))
+		return -EINVAL;
+
+	if (vmx_misc_cr3_count(data) > vmx_misc_cr3_count(vmx_misc))
+		return -EINVAL;
+
+	if (vmx_misc_max_msr(data) > vmx_misc_max_msr(vmx_misc))
+		return -EINVAL;
+
+	if (vmx_misc_mseg_revid(data) != vmx_misc_mseg_revid(vmx_misc))
+		return -EINVAL;
+
+	vmx->nested.nested_vmx_misc_low = data;
+	vmx->nested.nested_vmx_misc_high = data >> 32;
+	return 0;
+}
+
+static int vmx_restore_vmx_ept_vpid_cap(struct vcpu_vmx *vmx, u64 data)
+{
+	u64 vmx_ept_vpid_cap;
+
+	vmx_ept_vpid_cap = vmx_control_msr(vmx->nested.nested_vmx_ept_caps,
+					   vmx->nested.nested_vmx_vpid_caps);
+
+	/* Every bit is either reserved or a feature bit. */
+	if (!is_bitwise_subset(vmx_ept_vpid_cap, data, -1ULL))
+		return -EINVAL;
+
+	vmx->nested.nested_vmx_ept_caps = data;
+	vmx->nested.nested_vmx_vpid_caps = data >> 32;
+	return 0;
+}
+
+static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
+{
+	u64 *msr;
+
+	switch (msr_index) {
+	case MSR_IA32_VMX_CR0_FIXED0:
+		msr = &vmx->nested.nested_vmx_cr0_fixed0;
+		break;
+	case MSR_IA32_VMX_CR4_FIXED0:
+		msr = &vmx->nested.nested_vmx_cr4_fixed0;
+		break;
+	default:
+		BUG();
+	}
+
+	/*
+	 * 1 bits (which indicates bits which "must-be-1" during VMX operation)
+	 * must be 1 in the restored value.
+	 */
+	if (!is_bitwise_subset(data, *msr, -1ULL))
+		return -EINVAL;
+
+	*msr = data;
+	return 0;
+}
+
+/*
+ * Called when userspace is restoring VMX MSRs.
+ *
+ * Returns 0 on success, non-0 otherwise.
+ */
+static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
 	switch (msr_index) {
 	case MSR_IA32_VMX_BASIC:
+		return vmx_restore_vmx_basic(vmx, data);
+	case MSR_IA32_VMX_PINBASED_CTLS:
+	case MSR_IA32_VMX_PROCBASED_CTLS:
+	case MSR_IA32_VMX_EXIT_CTLS:
+	case MSR_IA32_VMX_ENTRY_CTLS:
+		/*
+		 * The "non-true" VMX capability MSRs are generated from the
+		 * "true" MSRs, so we do not support restoring them directly.
+		 *
+		 * If userspace wants to emulate VMX_BASIC[55]=0, userspace
+		 * should restore the "true" MSRs with the must-be-1 bits
+		 * set according to the SDM Vol 3. A.2 "RESERVED CONTROLS AND
+		 * DEFAULT SETTINGS".
+		 */
+		return -EINVAL;
+	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
+	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
+	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
+	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
+	case MSR_IA32_VMX_PROCBASED_CTLS2:
+		return vmx_restore_control_msr(vmx, msr_index, data);
+	case MSR_IA32_VMX_MISC:
+		return vmx_restore_vmx_misc(vmx, data);
+	case MSR_IA32_VMX_CR0_FIXED0:
+	case MSR_IA32_VMX_CR4_FIXED0:
+		return vmx_restore_fixed0_msr(vmx, msr_index, data);
+	case MSR_IA32_VMX_CR0_FIXED1:
+	case MSR_IA32_VMX_CR4_FIXED1:
+		/*
+		 * These MSRs are generated based on the vCPU's CPUID, so we
+		 * do not support restoring them directly.
+		 */
+		return -EINVAL;
+	case MSR_IA32_VMX_EPT_VPID_CAP:
+		return vmx_restore_vmx_ept_vpid_cap(vmx, data);
+	case MSR_IA32_VMX_VMCS_ENUM:
+		vmx->nested.nested_vmx_vmcs_enum = data;
+		return 0;
+	default:
 		/*
-		 * This MSR reports some information about VMX support. We
-		 * should return information about the VMX we emulate for the
-		 * guest, and the VMCS structure we give it - not about the
-		 * VMX support of the underlying hardware.
+		 * The rest of the VMX capability MSRs do not support restore.
 		 */
-		*pdata = VMCS12_REVISION | VMX_BASIC_TRUE_CTLS |
-			   ((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) |
-			   (VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT);
-		if (cpu_has_vmx_basic_inout())
-			*pdata |= VMX_BASIC_INOUT;
+		return -EINVAL;
+	}
+}
+
+/* Returns 0 on success, non-0 otherwise. */
+static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	switch (msr_index) {
+	case MSR_IA32_VMX_BASIC:
+		*pdata = vmx->nested.nested_vmx_basic;
 		break;
 	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
 	case MSR_IA32_VMX_PINBASED_CTLS:
@@ -2897,27 +3142,20 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 			vmx->nested.nested_vmx_misc_low,
 			vmx->nested.nested_vmx_misc_high);
 		break;
-	/*
-	 * These MSRs specify bits which the guest must keep fixed (on or off)
-	 * while L1 is in VMXON mode (in L1's root mode, or running an L2).
-	 * We picked the standard core2 setting.
-	 */
-#define VMXON_CR0_ALWAYSON	(X86_CR0_PE | X86_CR0_PG | X86_CR0_NE)
-#define VMXON_CR4_ALWAYSON	X86_CR4_VMXE
 	case MSR_IA32_VMX_CR0_FIXED0:
-		*pdata = VMXON_CR0_ALWAYSON;
+		*pdata = vmx->nested.nested_vmx_cr0_fixed0;
 		break;
 	case MSR_IA32_VMX_CR0_FIXED1:
-		*pdata = -1ULL;
+		*pdata = vmx->nested.nested_vmx_cr0_fixed1;
 		break;
 	case MSR_IA32_VMX_CR4_FIXED0:
-		*pdata = VMXON_CR4_ALWAYSON;
+		*pdata = vmx->nested.nested_vmx_cr4_fixed0;
 		break;
 	case MSR_IA32_VMX_CR4_FIXED1:
-		*pdata = -1ULL;
+		*pdata = vmx->nested.nested_vmx_cr4_fixed1;
 		break;
 	case MSR_IA32_VMX_VMCS_ENUM:
-		*pdata = 0x2e; /* highest index: VMX_PREEMPTION_TIMER_VALUE */
+		*pdata = vmx->nested.nested_vmx_vmcs_enum;
 		break;
 	case MSR_IA32_VMX_PROCBASED_CTLS2:
 		*pdata = vmx_control_msr(
@@ -3100,7 +3338,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			vmx_leave_nested(vcpu);
 		break;
 	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
-		return 1; /* they are read-only */
+		if (!msr_info->host_initiated)
+			return 1; /* they are read-only */
+		if (!nested_vmx_allowed(vcpu))
+			return 1;
+		return vmx_set_vmx_msr(vcpu, msr_index, data);
 	case MSR_IA32_XSS:
 		if (!vmx_xsaves_supported())
 			return 1;
-- 
2.8.0.rc3.226.g39d4020