Re: [RFC PATCH 12/18] KVM: x86/mmu: Introduce shadow_ux_mask

[Chao Gao <chao.gao@intel.com>]

>@@ -28,6 +28,7 @@ u64 __read_mostly shadow_host_writable_mask;
> u64 __read_mostly shadow_mmu_writable_mask;
> u64 __read_mostly shadow_nx_mask;
> u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */
>+u64 __read_mostly shadow_ux_mask;
> u64 __read_mostly shadow_user_mask;
> u64 __read_mostly shadow_accessed_mask;
> u64 __read_mostly shadow_dirty_mask;
>@@ -313,8 +314,14 @@ u64 make_huge_page_split_spte(struct kvm *kvm, u64 huge_spte,
> 		 * the page executable as the NX hugepage mitigation no longer
> 		 * applies.
> 		 */
>-		if ((role.access & ACC_EXEC_MASK) && is_nx_huge_page_enabled(kvm))
>+		if ((role.access & ACC_EXEC_MASK) && is_nx_huge_page_enabled(kvm)) {

is it possible that role.access has ACC_USER_EXEC_MASK set but not ACC_EXEC_MASK?
if so, this condition should be:

		if ((role.access & (ACC_EXEC_MASK | ACC_USER_EXEC_MASK)) &&
		    is_nx_huge_page_enabled(kvm)) {

> 			child_spte = make_spte_executable(child_spte);
>+			// TODO: For LKML: switch to vcpu->arch.pt_guest_exec_control? up
>+			// for suggestions on how best to toggle this.
>+			if (enable_pt_guest_exec_control &&

If enable_pt_guest_exec_control is 0, then shadow_ux_mask will also be 0. i.e.,
this check isn't needed.

>+			    role.access & ACC_USER_EXEC_MASK)
>+				child_spte |= shadow_ux_mask;

MBEC can be tracked in the kvm_mmu_page_role, then you can do:

			if (role.mbec_enabled && role.access & ACC_USER_EXEC_MASK)
				child_spte |= shadow_ux_mask;

>+		}
> 	}
> 
> 	return child_spte;
>@@ -326,7 +333,7 @@ u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled)
> 	u64 spte = SPTE_MMU_PRESENT_MASK;
> 
> 	spte |= __pa(child_pt) | shadow_present_mask | PT_WRITABLE_MASK |
>-		shadow_user_mask | shadow_x_mask | shadow_me_value;
>+		shadow_user_mask | shadow_x_mask | shadow_ux_mask | shadow_me_value;
> 
> 	if (ad_disabled)
> 		spte |= SPTE_TDP_AD_DISABLED;
>@@ -420,7 +427,8 @@ void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask)
> }
> EXPORT_SYMBOL_GPL(kvm_mmu_set_me_spte_mask);
> 
>-void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
>+void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only,
>+			   bool has_guest_exec_ctrl)
> {
> 	shadow_user_mask	= VMX_EPT_READABLE_MASK;
> 	shadow_accessed_mask	= has_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull;
>@@ -428,8 +436,14 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
> 	shadow_nx_mask		= 0ull;
> 	shadow_x_mask		= VMX_EPT_EXECUTABLE_MASK;
> 	/* VMX_EPT_SUPPRESS_VE_BIT is needed for W or X violation. */
>+	// For LKML Review:
>+	// Do we need to modify shadow_present_mask in the MBEC case?
> 	shadow_present_mask	=
> 		(has_exec_only ? 0ull : VMX_EPT_READABLE_MASK) | VMX_EPT_SUPPRESS_VE_BIT;

No, the SDM requires that present EPT entries have the VMX_EPT_READABLE_MASK
set if execute only translation is not supported. (The VMX_EPT_SUPPRESS_VE_BIT
is for TDX).

MBEC does not change this requirement.

>+
>+	shadow_ux_mask		=
>+		has_guest_exec_ctrl ? VMX_EPT_USER_EXECUTABLE_MASK : 0ull;
>+
> 	/*
> 	 * EPT overrides the host MTRRs, and so KVM must program the desired
> 	 * memtype directly into the SPTEs.  Note, this mask is just the mask
>@@ -484,6 +498,7 @@ void kvm_mmu_reset_all_pte_masks(void)
> 	shadow_dirty_mask	= PT_DIRTY_MASK;
> 	shadow_nx_mask		= PT64_NX_MASK;
> 	shadow_x_mask		= 0;
>+	shadow_ux_mask		= 0;
> 	shadow_present_mask	= PT_PRESENT_MASK;
> 
> 	/*
>diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
>index d9e22133b6d0..dc2f0dc9c46e 100644
>--- a/arch/x86/kvm/mmu/spte.h
>+++ b/arch/x86/kvm/mmu/spte.h
>@@ -171,6 +171,7 @@ extern u64 __read_mostly shadow_mmu_writable_mask;
> extern u64 __read_mostly shadow_nx_mask;
> extern u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */
> extern u64 __read_mostly shadow_user_mask;
>+extern u64 __read_mostly shadow_ux_mask;
> extern u64 __read_mostly shadow_accessed_mask;
> extern u64 __read_mostly shadow_dirty_mask;
> extern u64 __read_mostly shadow_mmio_value;
>diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
>index 0aadfa924045..d16e3f170258 100644
>--- a/arch/x86/kvm/vmx/vmx.c
>+++ b/arch/x86/kvm/vmx/vmx.c
>@@ -8544,7 +8544,8 @@ __init int vmx_hardware_setup(void)
> 
> 	if (enable_ept)
> 		kvm_mmu_set_ept_masks(enable_ept_ad_bits,
>-				      cpu_has_vmx_ept_execute_only());
>+				      cpu_has_vmx_ept_execute_only(),
>+				      enable_pt_guest_exec_control);
> 
> 	/*
> 	 * Setup shadow_me_value/shadow_me_mask to include MKTME KeyID
>-- 
>2.43.0
>