Re: [PATCH v10 11/41] KVM: guest_memfd: Ensure pages are not in use before conversion

@@ -1641,7 +1641,7 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
 	/* Pairs with the smp_wmb() in kvm_mmu_invalidate_end(). */
 	smp_rmb();
 
-	ret = kvm_gmem_get_pfn(kvm, s2fd->memslot, gfn, &pfn, &page, NULL);
+	ret = kvm_gmem_get_pfn(kvm, s2fd->memslot, gfn, &pfn, NULL);
 	if (ret) {
 		kvm_prepare_memory_fault_exit(s2fd->vcpu, s2fd->fault_ipa, PAGE_SIZE,
 					      write_fault, exec_fault, false);

@@ -1411,7 +1411,7 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
 		if (is_error_noslot_pfn(pfn) || (write_fault && !writable))
 			return -EFAULT;
 	} else {
-		ret = kvm_gmem_get_pfn(vcpu->kvm, memslot, gfn, &pfn, &page, NULL);
+		ret = kvm_gmem_get_pfn(vcpu->kvm, memslot, gfn, &pfn, NULL);
 		if (ret) {
 			kvm_prepare_memory_fault_exit(vcpu, vt->wr.pa, PAGE_SIZE,
 					      write_fault, false, false);

@@ -4603,8 +4603,7 @@ static int kvm_mmu_faultin_pfn_gmem(struct kvm_vcpu *vcpu,
 		return -EFAULT;
 	}
 
-	r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn,
-			     &fault->refcounted_page, &max_order);
+	r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, &max_order);
 	if (r) {
 		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
 		return r;

@@ -4060,7 +4060,7 @@ static void __sev_snp_reload_vmsa(struct kvm_vcpu *vcpu, gpa_t gpa)
 	 * The new VMSA will be private memory guest memory, so retrieve the
 	 * PFN from the gmem backend.
 	 */
-	if (kvm_gmem_get_pfn(vcpu->kvm, slot, gfn, &pfn, &page, NULL))
+	if (kvm_gmem_get_pfn(vcpu->kvm, slot, gfn, &pfn, NULL))
 		return;
 
 	read_lock(&kvm->mmu_lock);

@@ -5003,7 +5003,7 @@ void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
 	struct kvm_memory_slot *slot;
 	struct kvm *kvm = vcpu->kvm;
 	int order, rmp_level, ret;
-	struct page *page;
+	unsigned long mmu_seq;
 	bool assigned;
 	kvm_pfn_t pfn;
 	gfn_t gfn;

@@ -5030,7 +5030,10 @@ void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
 		return;
 	}
 
-	ret = kvm_gmem_get_pfn(kvm, slot, gfn, &pfn, &page, &order);
+	mmu_seq = kvm->mmu_invalidate_seq;
+	smp_rmb();
+
+	ret = kvm_gmem_get_pfn(kvm, slot, gfn, &pfn, &order);
 	if (ret) {
 		pr_warn_ratelimited("SEV: Unexpected RMP fault, no backing page for private GPA 0x%llx\n",
 				    gpa);

@@ -5041,7 +5044,7 @@ void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
 	if (ret || !assigned) {
 		pr_warn_ratelimited("SEV: Unexpected RMP fault, no assigned RMP entry found for GPA 0x%llx PFN 0x%llx error %d\n",
 				    gpa, pfn, ret);
-		goto out_no_trace;
+		return;
 	}
 
 	/*

@@ -5069,26 +5072,29 @@ void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
 	if (rmp_level == PG_LEVEL_4K)
 		goto out;
 
-	ret = snp_rmptable_psmash(pfn);
-	if (ret) {
-		/*
-		 * Look it up again. If it's 4K now then the PSMASH may have
-		 * raced with another process and the issue has already resolved
-		 * itself.
-		 */
-		if (!snp_lookup_rmpentry(pfn, &assigned, &rmp_level) &&
-		    assigned && rmp_level == PG_LEVEL_4K)
+	scoped_guard(read_lock)(&kvm->mmu_lock) {
+		if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn))
 			goto out;
 
-		pr_warn_ratelimited("SEV: Unable to split RMP entry for GPA 0x%llx PFN 0x%llx ret %d\n",
-				    gpa, pfn, ret);
+		ret = snp_rmptable_psmash(pfn);
+		if (ret) {
+			/*
+			 * Look it up again. If it's 4K now then the PSMASH may have
+			 * raced with another process and the issue has already
+			 * resolved itself.
+			 */
+			if (!snp_lookup_rmpentry(pfn, &assigned, &rmp_level) &&
+		    	    assigned && rmp_level == PG_LEVEL_4K)
+				goto out;
+
+			pr_warn_ratelimited("SEV: Unable to split RMP entry for GPA 0x%llx PFN 0x%llx ret %d\n",
+					    gpa, pfn, ret);
+		}
 	}
 
 	kvm_zap_gfn_range(kvm, gfn, gfn + PTRS_PER_PMD);
 out:
 	trace_kvm_rmp_fault(vcpu, gpa, pfn, error_code, rmp_level, ret);
-out_no_trace:
-	kvm_release_page_unused(page);
 }
 
 static bool is_pfn_range_shared(kvm_pfn_t start, kvm_pfn_t end)

@@ -2586,13 +2586,11 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
 
 #ifdef CONFIG_KVM_GUEST_MEMFD
 int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
-		     gfn_t gfn, kvm_pfn_t *pfn, struct page **page,
-		     int *max_order);
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order);
 #else
 static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn,
-				   kvm_pfn_t *pfn, struct page **page,
-				   int *max_order)
+				   kvm_pfn_t *pfn, int *max_order)
 {
 	KVM_BUG_ON(1, kvm);
 	return -EIO;

@@ -751,8 +751,7 @@ static struct folio *__kvm_gmem_get_pfn(struct file *file,
 }
 
 int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
-		     gfn_t gfn, kvm_pfn_t *pfn, struct page **page,
-		     int *max_order)
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
 {
 	pgoff_t index = kvm_gmem_get_index(slot, gfn);
 	struct folio *folio;

@@ -780,12 +779,7 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 #endif
 
 	folio_unlock(folio);
-
-	if (!r)
-		*page = folio_file_page(folio, index);
-	else
-		folio_put(folio);
-
+	folio_put(folio);
 	return r;
 }
 EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn);