3 files changed, 94 insertions, 3 deletions

diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 40264f60b0da..f4073106e1f3 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -148,4 +148,6 @@ void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
 			     unsigned long gaddr, unsigned long vmaddr);
 int gmap_mark_unmergeable(void);
 void s390_reset_acc(struct mm_struct *mm);
+void s390_unlist_old_asce(struct gmap *gmap);
+int s390_replace_asce(struct gmap *gmap);
 #endif /* _ASM_S390_GMAP_H */
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index 822887887222..c0e00e94ee22 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -163,10 +163,13 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 	atomic_set(&kvm->mm->context.is_protected, 0);
 	KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM: rc %x rrc %x", *rc, *rrc);
 	WARN_ONCE(cc, "protvirt destroy vm failed rc %x rrc %x", *rc, *rrc);
-	/* Inteded memory leak on "impossible" error */
-	if (!cc)
+	/* Intended memory leak on "impossible" error */
+	if (!cc) {
 		kvm_s390_pv_dealloc_vm(kvm);
-	return cc ? -EIO : 0;
+		return 0;
+	}
+	s390_replace_asce(kvm->arch.gmap);
+	return -EIO;
 }
 
 int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 2db097c14cec..03e561608eed 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2721,3 +2721,89 @@ void s390_reset_acc(struct mm_struct *mm)
 	mmput(mm);
 }
 EXPORT_SYMBOL_GPL(s390_reset_acc);
+
+/**
+ * s390_unlist_old_asce - Remove the topmost level of page tables from the
+ * list of page tables of the gmap.
+ * @gmap: the gmap whose table is to be removed
+ *
+ * On s390x, KVM keeps a list of all pages containing the page tables of the
+ * gmap (the CRST list). This list is used at tear down time to free all
+ * pages that are now not needed anymore.
+ *
+ * This function removes the topmost page of the tree (the one pointed to by
+ * the ASCE) from the CRST list.
+ *
+ * This means that it will not be freed when the VM is torn down, and needs
+ * to be handled separately by the caller, unless a leak is actually
+ * intended. Notice that this function will only remove the page from the
+ * list, the page will still be used as a top level page table (and ASCE).
+ */
+void s390_unlist_old_asce(struct gmap *gmap)
+{
+	struct page *old;
+
+	old = virt_to_page(gmap->table);
+	spin_lock(&gmap->guest_table_lock);
+	list_del(&old->lru);
+	/*
+	 * Sometimes the topmost page might need to be "removed" multiple
+	 * times, for example if the VM is rebooted into secure mode several
+	 * times concurrently, or if s390_replace_asce fails after calling
+	 * s390_remove_old_asce and is attempted again later. In that case
+	 * the old asce has been removed from the list, and therefore it
+	 * will not be freed when the VM terminates, but the ASCE is still
+	 * in use and still pointed to.
+	 * A subsequent call to replace_asce will follow the pointer and try
+	 * to remove the same page from the list again.
+	 * Therefore it's necessary that the page of the ASCE has valid
+	 * pointers, so list_del can work (and do nothing) without
+	 * dereferencing stale or invalid pointers.
+	 */
+	INIT_LIST_HEAD(&old->lru);
+	spin_unlock(&gmap->guest_table_lock);
+}
+EXPORT_SYMBOL_GPL(s390_unlist_old_asce);
+
+/**
+ * s390_replace_asce - Try to replace the current ASCE of a gmap with a copy
+ * @gmap: the gmap whose ASCE needs to be replaced
+ *
+ * If the allocation of the new top level page table fails, the ASCE is not
+ * replaced.
+ * In any case, the old ASCE is always removed from the gmap CRST list.
+ * Therefore the caller has to make sure to save a pointer to it
+ * beforehand, unless a leak is actually intended.
+ */
+int s390_replace_asce(struct gmap *gmap)
+{
+	unsigned long asce;
+	struct page *page;
+	void *table;
+
+	s390_unlist_old_asce(gmap);
+
+	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
+	if (!page)
+		return -ENOMEM;
+	table = page_to_virt(page);
+	memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT));
+
+	/*
+	 * The caller has to deal with the old ASCE, but here we make sure
+	 * the new one is properly added to the CRST list, so that
+	 * it will be freed when the VM is torn down.
+	 */
+	spin_lock(&gmap->guest_table_lock);
+	list_add(&page->lru, &gmap->crst_list);
+	spin_unlock(&gmap->guest_table_lock);
+
+	/* Set new table origin while preserving existing ASCE control bits */
+	asce = (gmap->asce & ~_ASCE_ORIGIN) | __pa(table);
+	WRITE_ONCE(gmap->asce, asce);
+	WRITE_ONCE(gmap->mm->context.gmap_asce, asce);
+	WRITE_ONCE(gmap->table, table);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(s390_replace_asce);