diff mbox series

[RFC,15/18] KVM: x86/mmu: Extend make_spte to understand MBEC

Message ID 20250313203702.575156-16-jon@nutanix.com (mailing list archive)
State New
Headers show
Series KVM: VMX: Introduce Intel Mode-Based Execute Control (MBEC) | expand

Commit Message

Jon Kohler March 13, 2025, 8:36 p.m. UTC 
Extend make_spte to mask in and out bits depending on MBEC enablement.

Note: For the RFC/v1 series, I've added several 'For Review' items that
may require a bit deeper inspection, as well as some long winded
comments/annotations. These will be cleaned up for the next iteration
of the series after initial review.

Signed-off-by: Jon Kohler <jon@nutanix.com>
Co-developed-by: Sergey Dyasli <sergey.dyasli@nutanix.com>
Signed-off-by: Sergey Dyasli <sergey.dyasli@nutanix.com>

---
 arch/x86/kvm/mmu/paging_tmpl.h |  3 +++
 arch/x86/kvm/mmu/spte.c        | 30 ++++++++++++++++++++++++++----
 2 files changed, 29 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index a3a5cacda614..7675239f2dd1 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -840,6 +840,9 @@  static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 		 * then we should prevent the kernel from executing it
 		 * if SMEP is enabled.
 		 */
+		// FOR REVIEW:
+		// ACC_USER_EXEC_MASK seems not necessary to add here since
+		// SMEP is for kernel-only.
 		if (is_cr4_smep(vcpu->arch.mmu))
 			walker.pte_access &= ~ACC_EXEC_MASK;
 	}
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 6f4994b3e6d0..89bdae3f9ada 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -178,6 +178,9 @@  bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	else if (kvm_mmu_page_ad_need_write_protect(sp))
 		spte |= SPTE_TDP_AD_WRPROT_ONLY;
 
+	// For LKML Review:
+	// In MBEC case, you can have exec only and also bit 10
+	// set for user exec only. Do we need to cater for that here?
 	spte |= shadow_present_mask;
 	if (!prefetch)
 		spte |= spte_shadow_accessed_mask(spte);
@@ -197,12 +200,31 @@  bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	if (level > PG_LEVEL_4K && (pte_access & ACC_EXEC_MASK) &&
 	    is_nx_huge_page_enabled(vcpu->kvm)) {
 		pte_access &= ~ACC_EXEC_MASK;
+		if (vcpu->arch.pt_guest_exec_control)
+			pte_access &= ~ACC_USER_EXEC_MASK;
 	}
 
-	if (pte_access & ACC_EXEC_MASK)
-		spte |= shadow_x_mask;
-	else
-		spte |= shadow_nx_mask;
+	// For LKML Review:
+	// We could probably optimize the logic here, but typing it out
+	// long hand for now to make it clear how we're changing the control
+	// flow to support MBEC.
+	if (!vcpu->arch.pt_guest_exec_control) { // non-mbec logic
+		if (pte_access & ACC_EXEC_MASK)
+			spte |= shadow_x_mask;
+		else
+			spte |= shadow_nx_mask;
+	} else { // mbec logic
+		if (pte_access & ACC_EXEC_MASK) { /* mbec: kernel exec */
+			if (pte_access & ACC_USER_EXEC_MASK)
+				spte |= shadow_x_mask | shadow_ux_mask; // KMX = 1, UMX = 1
+			else
+				spte |= shadow_x_mask;  // KMX = 1, UMX = 0
+		} else if (pte_access & ACC_USER_EXEC_MASK) { /* mbec: user exec, no kernel exec */
+			spte |= shadow_ux_mask; // KMX = 0, UMX = 1
+		} else { /* mbec: nx */
+			spte |= shadow_nx_mask; // KMX = 0, UMX = 0
+		}
+	}
 
 	if (pte_access & ACC_USER_MASK)
 		spte |= shadow_user_mask;