[PATCH 15/28] KVM: VMX: enable use of MBEC

[Paolo Bonzini <pbonzini@redhat.com>]

If available, set SECONDARY_EXEC_MODE_BASED_EPT_EXEC in the secondary
execution controls.

XS and XU are configured separately even if host does not support MBEC,
to avoid confusion where an L1 hypervisor sets bit 10 in its EPT
(knowing the non-MBEC hardware ignores it) but clears bit 2 to make the
page non-executable, and KVM sets the X bit via shadow_xu_mask.

Tested-by: David Riley <d.riley@proxmox.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/vmx.h      |  3 +++
 arch/x86/kvm/mmu.h              |  5 +++++
 arch/x86/kvm/mmu/spte.c         |  2 +-
 arch/x86/kvm/mmu/spte.h         |  5 +++--
 arch/x86/kvm/vmx/capabilities.h |  7 +++++++
 arch/x86/kvm/vmx/common.h       | 10 +++++-----
 arch/x86/kvm/vmx/main.c         |  9 +++++++++
 arch/x86/kvm/vmx/nested.c       |  1 +
 arch/x86/kvm/vmx/vmx.c          | 16 +++++++++++++++-
 arch/x86/kvm/vmx/vmx.h          |  1 +
 arch/x86/kvm/vmx/x86_ops.h      |  1 +
 11 files changed, 51 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 2b30b921b375..54aa5be50df9 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -619,9 +619,12 @@ enum vm_entry_failure_code {
 #define EPT_VIOLATION_GVA_TRANSLATED	BIT(8)
 
 #define EPT_VIOLATION_RWX_TO_PROT(__epte) (((__epte) & VMX_EPT_RWX_MASK) << 3)
+#define EPT_VIOLATION_USER_EXEC_TO_PROT(__epte) (((__epte) & VMX_EPT_USER_EXECUTABLE_MASK) >> 4)
 
 static_assert(EPT_VIOLATION_RWX_TO_PROT(VMX_EPT_RWX_MASK) ==
 	      (EPT_VIOLATION_PROT_READ | EPT_VIOLATION_PROT_WRITE | EPT_VIOLATION_PROT_EXEC));
+static_assert(EPT_VIOLATION_USER_EXEC_TO_PROT(VMX_EPT_USER_EXECUTABLE_MASK) ==
+	      (EPT_VIOLATION_PROT_USER_EXEC));
 
 /*
  * Exit Qualifications for NOTIFY VM EXIT
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index d8c13e43c2d7..23bc5b18efd0 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -83,6 +83,11 @@ static inline gfn_t kvm_mmu_max_gfn(void)
 	return (1ULL << (max_gpa_bits - PAGE_SHIFT)) - 1;
 }
 
+static inline bool mmu_has_mbec(struct kvm_mmu *mmu)
+{
+	return mmu->root_role.cr4_smep;
+}
+
 u8 kvm_mmu_get_max_tdp_level(void);
 
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask);
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 4575dd77f854..09e6f494dcf4 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -525,7 +525,7 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits)
 	shadow_xu_mask		= VMX_EPT_USER_EXECUTABLE_MASK;
 	shadow_present_mask	= VMX_EPT_SUPPRESS_VE_BIT;
 
-	shadow_acc_track_mask	= VMX_EPT_RWX_MASK;
+	shadow_acc_track_mask	= VMX_EPT_RWX_MASK | VMX_EPT_USER_EXECUTABLE_MASK;
 	shadow_host_writable_mask = EPT_SPTE_HOST_WRITABLE;
 	shadow_mmu_writable_mask  = EPT_SPTE_MMU_WRITABLE;
 
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 0ed690f78e17..f5261d993eac 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -24,7 +24,7 @@
  * - bits 55 (EPT only): MMU-writable
  * - bits 56-59: unused
  * - bits 60-61: type of A/D tracking
- * - bits 62: unused
+ * - bits 62 (EPT only): saved XU bit for disabled AD
  */
 
 /*
@@ -65,7 +65,8 @@ static_assert(SPTE_TDP_AD_ENABLED == 0);
  * must not overlap the A/D type mask.
  */
 #define SHADOW_ACC_TRACK_SAVED_BITS_MASK (VMX_EPT_READABLE_MASK | \
-					  VMX_EPT_EXECUTABLE_MASK)
+					  VMX_EPT_EXECUTABLE_MASK | \
+					  VMX_EPT_USER_EXECUTABLE_MASK)
 #define SHADOW_ACC_TRACK_SAVED_BITS_SHIFT 52
 #define SHADOW_ACC_TRACK_SAVED_MASK	(SHADOW_ACC_TRACK_SAVED_BITS_MASK << \
 					 SHADOW_ACC_TRACK_SAVED_BITS_SHIFT)
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 7e59eb0f41bb..07469d1cfe74 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -15,6 +15,7 @@ extern bool __read_mostly enable_ept;
 extern bool __read_mostly enable_unrestricted_guest;
 extern bool __read_mostly enable_ept_ad_bits;
 extern bool __read_mostly enable_pml;
+extern bool __read_mostly enable_mbec;
 extern int __read_mostly pt_mode;
 
 #define PT_MODE_SYSTEM		0
@@ -406,4 +407,10 @@ static inline bool cpu_has_notify_vmexit(void)
 		SECONDARY_EXEC_NOTIFY_VM_EXITING;
 }
 
+static inline bool cpu_has_ept_mbec(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_MODE_BASED_EPT_EXEC;
+}
+
 #endif /* __KVM_X86_VMX_CAPS_H */
diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h
index 1afbf272efae..40fa72f31fc7 100644
--- a/arch/x86/kvm/vmx/common.h
+++ b/arch/x86/kvm/vmx/common.h
@@ -91,15 +91,15 @@ static inline int __vmx_handle_ept_violation(struct kvm_vcpu *vcpu, gpa_t gpa,
 	/* Is it a fetch fault? */
 	error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR)
 		      ? PFERR_FETCH_MASK : 0;
-	/*
-	 * ept page table entry is present?
-	 * note: unconditionally clear USER_EXEC until mode-based
-	 * execute control is implemented
-	 */
+	/* ept page table entry is present?  */
 	error_code |= (exit_qualification &
 		       (EPT_VIOLATION_PROT_MASK & ~EPT_VIOLATION_PROT_USER_EXEC))
 		      ? PFERR_PRESENT_MASK : 0;
 
+	if (mmu_has_mbec(vcpu->arch.mmu))
+		error_code |= (exit_qualification & EPT_VIOLATION_PROT_USER_EXEC)
+			      ? PFERR_PRESENT_MASK : 0;
+
 	if (exit_qualification & EPT_VIOLATION_GVA_IS_VALID)
 		error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ?
 			      PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index dbebddf648be..83d9921277ea 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -755,6 +755,14 @@ static int vt_set_identity_map_addr(struct kvm *kvm, u64 ident_addr)
 	return vmx_set_identity_map_addr(kvm, ident_addr);
 }
 
+static bool vt_tdp_has_smep(struct kvm *kvm)
+{
+	if (is_td(kvm))
+		return false;
+
+	return vmx_tdp_has_smep(kvm);
+}
+
 static u64 vt_get_l2_tsc_offset(struct kvm_vcpu *vcpu)
 {
 	/* TDX doesn't support L2 guest at the moment. */
@@ -966,6 +974,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.set_tss_addr = vt_op(set_tss_addr),
 	.set_identity_map_addr = vt_op(set_identity_map_addr),
 	.get_mt_mask = vmx_get_mt_mask,
+	.tdp_has_smep = vt_op(tdp_has_smep),
 
 	.get_exit_info = vt_op(get_exit_info),
 	.get_entry_info = vt_op(get_entry_info),
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index cd1924c6e075..299d4ca60fb3 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2440,6 +2440,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 				  SECONDARY_EXEC_APIC_REGISTER_VIRT |
 				  SECONDARY_EXEC_ENABLE_VMFUNC |
+				  SECONDARY_EXEC_MODE_BASED_EPT_EXEC |
 				  SECONDARY_EXEC_DESC);
 
 		if (nested_cpu_has(vmcs12,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 337bbfecc021..72a75fa33c93 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -114,6 +114,9 @@ module_param(emulate_invalid_guest_state, bool, 0444);
 static bool __read_mostly fasteoi = 1;
 module_param(fasteoi, bool, 0444);
 
+bool __read_mostly enable_mbec = 1;
+module_param_named(mbec, enable_mbec, bool, 0444);
+
 module_param(enable_apicv, bool, 0444);
 module_param(enable_ipiv, bool, 0444);
 
@@ -2773,6 +2776,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 			return -EIO;
 
 		vmx_cap->ept = 0;
+		_cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_MODE_BASED_EPT_EXEC;
 		_cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE;
 	}
 	if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) &&
@@ -4735,6 +4739,9 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 	 */
 	exec_control &= ~SECONDARY_EXEC_ENABLE_VMFUNC;
 
+	if (!enable_mbec)
+		exec_control &= ~SECONDARY_EXEC_MODE_BASED_EPT_EXEC;
+
 	/* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP,
 	 * in vmx_set_cr4.  */
 	exec_control &= ~SECONDARY_EXEC_DESC;
@@ -7823,6 +7830,11 @@ u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT);
 }
 
+bool vmx_tdp_has_smep(struct kvm *kvm)
+{
+	return enable_mbec;
+}
+
 static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl)
 {
 	/*
@@ -8622,6 +8634,8 @@ __init int vmx_hardware_setup(void)
 
 	if (!cpu_has_vmx_ept_ad_bits() || !enable_ept)
 		enable_ept_ad_bits = 0;
+	if (!cpu_has_ept_mbec() || !enable_ept)
+		enable_mbec = 0;
 
 	if (!cpu_has_vmx_unrestricted_guest() || !enable_ept)
 		enable_unrestricted_guest = 0;
@@ -8683,7 +8697,7 @@ __init int vmx_hardware_setup(void)
 	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
 
 	if (enable_ept)
-		kvm_mmu_set_ept_masks(enable_ept_ad_bits);
+		kvm_mmu_set_ept_masks(enable_ept_ad_bits, enable_mbec);
 	else
 		vt_x86_ops.get_mt_mask = NULL;
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index db84e8001da5..0a4e263c4095 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -567,6 +567,7 @@ static inline u8 vmx_get_rvi(void)
 	 SECONDARY_EXEC_ENABLE_VMFUNC |					\
 	 SECONDARY_EXEC_BUS_LOCK_DETECTION |				\
 	 SECONDARY_EXEC_NOTIFY_VM_EXITING |				\
+	 SECONDARY_EXEC_MODE_BASED_EPT_EXEC |				\
 	 SECONDARY_EXEC_ENCLS_EXITING |					\
 	 SECONDARY_EXEC_EPT_VIOLATION_VE)
 
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index d09abeac2b56..69cf276be88e 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -103,6 +103,7 @@ void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
 int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr);
 u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
+bool vmx_tdp_has_smep(struct kvm *kvm);
 
 void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
 		       u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code);
-- 
2.52.0