1 files changed, 47 insertions, 32 deletions

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 37363900297d..e03225e707b2 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -499,6 +499,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	mmu_set_spte(vcpu, spte, pte_access, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn,
 		     true, true);
 
+	kvm_release_pfn_clean(pfn);
 	return true;
 }
 
@@ -572,12 +573,14 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *gw,
 			 int write_fault, int hlevel,
-			 kvm_pfn_t pfn, bool map_writable, bool prefault)
+			 kvm_pfn_t pfn, bool map_writable, bool prefault,
+			 bool lpage_disallowed)
 {
 	struct kvm_mmu_page *sp = NULL;
 	struct kvm_shadow_walk_iterator it;
 	unsigned direct_access, access = gw->pt_access;
-	int top_level, emulate;
+	int top_level, ret;
+	gfn_t gfn, base_gfn;
 
 	direct_access = gw->pte_access;
 
@@ -622,36 +625,49 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			link_shadow_page(vcpu, it.sptep, sp);
 	}
 
-	for (;
-	     shadow_walk_okay(&it) && it.level > hlevel;
-	     shadow_walk_next(&it)) {
-		gfn_t direct_gfn;
+	/*
+	 * FNAME(page_fault) might have clobbered the bottom bits of
+	 * gw->gfn, restore them from the virtual address.
+	 */
+	gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT);
+	base_gfn = gfn;
 
+	trace_kvm_mmu_spte_requested(addr, gw->level, pfn);
+
+	for (; shadow_walk_okay(&it); shadow_walk_next(&it)) {
 		clear_sp_write_flooding_count(it.sptep);
-		validate_direct_spte(vcpu, it.sptep, direct_access);
 
-		drop_large_spte(vcpu, it.sptep);
+		/*
+		 * We cannot overwrite existing page tables with an NX
+		 * large page, as the leaf could be executable.
+		 */
+		disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel);
 
-		if (is_shadow_present_pte(*it.sptep))
-			continue;
+		base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+		if (it.level == hlevel)
+			break;
 
-		direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+		validate_direct_spte(vcpu, it.sptep, direct_access);
 
-		sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1,
-				      true, direct_access);
-		link_shadow_page(vcpu, it.sptep, sp);
+		drop_large_spte(vcpu, it.sptep);
+
+		if (!is_shadow_present_pte(*it.sptep)) {
+			sp = kvm_mmu_get_page(vcpu, base_gfn, addr,
+					      it.level - 1, true, direct_access);
+			link_shadow_page(vcpu, it.sptep, sp);
+			if (lpage_disallowed)
+				account_huge_nx_page(vcpu->kvm, sp);
+		}
 	}
 
-	clear_sp_write_flooding_count(it.sptep);
-	emulate = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault,
-			       it.level, gw->gfn, pfn, prefault, map_writable);
+	ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault,
+			   it.level, base_gfn, pfn, prefault, map_writable);
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
-
-	return emulate;
+	++vcpu->stat.pf_fixed;
+	return ret;
 
 out_gpte_changed:
-	kvm_release_pfn_clean(pfn);
-	return 0;
+	return RET_PF_RETRY;
 }
 
  /*
@@ -717,9 +733,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	int r;
 	kvm_pfn_t pfn;
 	int level = PT_PAGE_TABLE_LEVEL;
-	bool force_pt_level = false;
 	unsigned long mmu_seq;
 	bool map_writable, is_self_change_mapping;
+	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
+				is_nx_huge_page_enabled();
+	bool force_pt_level = lpage_disallowed;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
@@ -746,12 +764,12 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 		if (!prefault)
 			inject_page_fault(vcpu, &walker.fault);
 
-		return 0;
+		return RET_PF_RETRY;
 	}
 
 	if (page_fault_handle_page_track(vcpu, error_code, walker.gfn)) {
 		shadow_page_table_clear_flood(vcpu, addr);
-		return 1;
+		return RET_PF_EMULATE;
 	}
 
 	vcpu->arch.write_fault_to_shadow_pgtable = false;
@@ -773,7 +791,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 
 	if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, write_fault,
 			 &map_writable))
-		return 0;
+		return RET_PF_RETRY;
 
 	if (handle_abnormal_pfn(vcpu, mmu_is_nested(vcpu) ? 0 : addr,
 				walker.gfn, pfn, walker.pte_access, &r))
@@ -799,6 +817,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 			walker.pte_access &= ~ACC_EXEC_MASK;
 	}
 
+	r = RET_PF_RETRY;
 	spin_lock(&vcpu->kvm->mmu_lock);
 	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
 		goto out_unlock;
@@ -806,19 +825,15 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
 	make_mmu_pages_available(vcpu);
 	if (!force_pt_level)
-		transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level);
+		transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level);
 	r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
-			 level, pfn, map_writable, prefault);
-	++vcpu->stat.pf_fixed;
+			 level, pfn, map_writable, prefault, lpage_disallowed);
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
-	spin_unlock(&vcpu->kvm->mmu_lock);
-
-	return r;
 
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	kvm_release_pfn_clean(pfn);
-	return 0;
+	return r;
 }
 
 static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp)