kvm: mmu: don't set the present bit unconditionally

To support execute only mappings on behalf of L1
hypervisors, we need to teach set_spte() to honor all three of
L1's XWR bits.  As a start, add a new variable "shadow_present_mask"
that will be set for non-EPT shadow paging and clear for EPT.

Signed-off-by: Bandan Das <bsd@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -1031,7 +1031,7 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_init_vm(struct kvm *kvm);
 void kvm_mmu_uninit_vm(struct kvm *kvm);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask);
+		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask);
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm,

arch/x86/kvm/mmu.c

@@ -175,6 +175,7 @@ static u64 __read_mostly shadow_user_mask;
 static u64 __read_mostly shadow_accessed_mask;
 static u64 __read_mostly shadow_dirty_mask;
 static u64 __read_mostly shadow_mmio_mask;
+static u64 __read_mostly shadow_present_mask;
 
 static void mmu_spte_set(u64 *sptep, u64 spte);
 static void mmu_free_roots(struct kvm_vcpu *vcpu);
@@ -282,13 +283,14 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
 }
 
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask)
+		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask)
 {
 	shadow_user_mask = user_mask;
 	shadow_accessed_mask = accessed_mask;
 	shadow_dirty_mask = dirty_mask;
 	shadow_nx_mask = nx_mask;
 	shadow_x_mask = x_mask;
+	shadow_present_mask = p_mask;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
@@ -2245,10 +2247,9 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
 {
 	u64 spte;
 
-	BUILD_BUG_ON(VMX_EPT_READABLE_MASK != PT_PRESENT_MASK ||
-			VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
+	BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
 
-	spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK |
+	spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK |
 	       shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
 
 	mmu_spte_set(sptep, spte);
@@ -2515,13 +2516,13 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    gfn_t gfn, kvm_pfn_t pfn, bool speculative,
 		    bool can_unsync, bool host_writable)
 {
-	u64 spte;
+	u64 spte = 0;
 	int ret = 0;
 
 	if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access))
 		return 0;
 
-	spte = PT_PRESENT_MASK;
+	spte |= shadow_present_mask;
 	if (!speculative)
 		spte |= shadow_accessed_mask;
 

arch/x86/kvm/vmx.c

@@ -6473,6 +6473,7 @@ static __init int hardware_setup(void)
 			(enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull,
 			(enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull,
 			0ull, VMX_EPT_EXECUTABLE_MASK);
+			0ull, VMX_EPT_EXECUTABLE_MASK, VMX_EPT_READABLE_MASK);
 		ept_set_mmio_spte_mask();
 		kvm_enable_tdp();
 	} else

arch/x86/kvm/x86.c

@@ -5878,8 +5878,8 @@ int kvm_arch_init(void *opaque)
 	kvm_x86_ops = ops;
 
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
-			PT_DIRTY_MASK, PT64_NX_MASK, 0);
-
+			PT_DIRTY_MASK, PT64_NX_MASK, 0,
+			PT_PRESENT_MASK);
 	kvm_timer_init();
 
 	perf_register_guest_info_callbacks(&kvm_guest_cbs);