1 files changed, 49 insertions, 39 deletions

diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 97b21e7fd013..4e1ef0473663 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -128,6 +128,21 @@ static inline int FNAME(is_present_gpte)(unsigned long pte)
 #endif
 }
 
+static bool FNAME(is_bad_mt_xwr)(struct rsvd_bits_validate *rsvd_check, u64 gpte)
+{
+#if PTTYPE != PTTYPE_EPT
+	return false;
+#else
+	return __is_bad_mt_xwr(rsvd_check, gpte);
+#endif
+}
+
+static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
+{
+	return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level) ||
+	       FNAME(is_bad_mt_xwr)(&mmu->guest_rsvd_check, gpte);
+}
+
 static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			       pt_element_t __user *ptep_user, unsigned index,
 			       pt_element_t orig_pte, pt_element_t new_pte)
@@ -175,9 +190,6 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
 				  struct kvm_mmu_page *sp, u64 *spte,
 				  u64 gpte)
 {
-	if (is_rsvd_bits_set(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
-		goto no_present;
-
 	if (!FNAME(is_present_gpte)(gpte))
 		goto no_present;
 
@@ -186,6 +198,9 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
 	    !(gpte & PT_GUEST_ACCESSED_MASK))
 		goto no_present;
 
+	if (FNAME(is_rsvd_bits_set)(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+		goto no_present;
+
 	return false;
 
 no_present:
@@ -291,11 +306,11 @@ static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte)
 }
 
 /*
- * Fetch a guest pte for a guest virtual address
+ * Fetch a guest pte for a guest virtual address, or for an L2's GPA.
  */
 static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-				    gva_t addr, u32 access)
+				    gpa_t addr, u32 access)
 {
 	int ret;
 	pt_element_t pte;
@@ -400,7 +415,7 @@ retry_walk:
 		if (unlikely(!FNAME(is_present_gpte)(pte)))
 			goto error;
 
-		if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) {
+		if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte, walker->level))) {
 			errcode = PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
 			goto error;
 		}
@@ -496,7 +511,7 @@ error:
 }
 
 static int FNAME(walk_addr)(struct guest_walker *walker,
-			    struct kvm_vcpu *vcpu, gva_t addr, u32 access)
+			    struct kvm_vcpu *vcpu, gpa_t addr, u32 access)
 {
 	return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
 					access);
@@ -611,17 +626,17 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
  * If the guest tries to write a write-protected page, we need to
  * emulate this operation, return 1 to indicate this case.
  */
-static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
+static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 			 struct guest_walker *gw,
-			 int write_fault, int hlevel,
+			 int write_fault, int max_level,
 			 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, ret;
-	gfn_t gfn, base_gfn;
+	int top_level, hlevel, ret;
+	gfn_t base_gfn = gw->gfn;
 
 	direct_access = gw->pte_access;
 
@@ -637,7 +652,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	if (FNAME(gpte_changed)(vcpu, gw, top_level))
 		goto out_gpte_changed;
 
-	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
+	if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)))
 		goto out_gpte_changed;
 
 	for (shadow_walk_init(&it, vcpu, addr);
@@ -666,12 +681,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			link_shadow_page(vcpu, it.sptep, sp);
 	}
 
-	/*
-	 * 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;
+	hlevel = kvm_mmu_hugepage_adjust(vcpu, gw->gfn, max_level, &pfn);
 
 	trace_kvm_mmu_spte_requested(addr, gw->level, pfn);
 
@@ -682,9 +692,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 		 * We cannot overwrite existing page tables with an NX
 		 * large page, as the leaf could be executable.
 		 */
-		disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel);
+		disallowed_hugepage_adjust(it, gw->gfn, &pfn, &hlevel);
 
-		base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+		base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
 		if (it.level == hlevel)
 			break;
 
@@ -765,7 +775,7 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
  *  Returns: 1 if we need to emulate the instruction, 0 otherwise, or
  *           a negative value on error.
  */
-static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
+static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 			     bool prefault)
 {
 	int write_fault = error_code & PFERR_WRITE_MASK;
@@ -773,12 +783,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	struct guest_walker walker;
 	int r;
 	kvm_pfn_t pfn;
-	int level = PT_PAGE_TABLE_LEVEL;
 	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;
+	int max_level;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
@@ -818,14 +827,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu,
 	      &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable);
 
-	if (walker.level >= PT_DIRECTORY_LEVEL && !is_self_change_mapping) {
-		level = mapping_level(vcpu, walker.gfn, &force_pt_level);
-		if (likely(!force_pt_level)) {
-			level = min(walker.level, level);
-			walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1);
-		}
-	} else
-		force_pt_level = true;
+	if (lpage_disallowed || is_self_change_mapping)
+		max_level = PT_PAGE_TABLE_LEVEL;
+	else
+		max_level = walker.level;
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
@@ -865,10 +870,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
 	if (make_mmu_pages_available(vcpu) < 0)
 		goto out_unlock;
-	if (!force_pt_level)
-		transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level);
-	r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
-			 level, pfn, map_writable, prefault, lpage_disallowed);
+	r = FNAME(fetch)(vcpu, addr, &walker, write_fault, max_level, pfn,
+			 map_writable, prefault, lpage_disallowed);
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
 
 out_unlock:
@@ -945,18 +948,19 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 	spin_unlock(&vcpu->kvm->mmu_lock);
 }
 
-static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
+/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */
+static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access,
 			       struct x86_exception *exception)
 {
 	struct guest_walker walker;
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
-	r = FNAME(walk_addr)(&walker, vcpu, vaddr, access);
+	r = FNAME(walk_addr)(&walker, vcpu, addr, access);
 
 	if (r) {
 		gpa = gfn_to_gpa(walker.gfn);
-		gpa |= vaddr & ~PAGE_MASK;
+		gpa |= addr & ~PAGE_MASK;
 	} else if (exception)
 		*exception = walker.fault;
 
@@ -964,7 +968,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
 }
 
 #if PTTYPE != PTTYPE_EPT
-static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
+/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */
+static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr,
 				      u32 access,
 				      struct x86_exception *exception)
 {
@@ -972,6 +977,11 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
+#ifndef CONFIG_X86_64
+	/* A 64-bit GVA should be impossible on 32-bit KVM. */
+	WARN_ON_ONCE(vaddr >> 32);
+#endif
+
 	r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access);
 
 	if (r) {