When a protected VM is created, the topmost level of page tables of its
ASCE is marked by the Ultravisor; any attempt to use that memory for
protected virtualization will result in failure.
Only a successful Destroy Configuration UVC will remove the marking.
When the Destroy Configuration UVC fails, the topmost level of page
tables of the VM does not get its marking cleared; to avoid issues it
must not be used again.
This is a permanent error and the page becomes in practice unusable, so
we set it aside and leak it.
Signed-off-by: Claudio Imbrenda <imbrenda@xxxxxxxxxxxxx>
---
arch/s390/include/asm/gmap.h | 2 ++
arch/s390/kvm/pv.c | 4 ++-
arch/s390/mm/gmap.c | 55 ++++++++++++++++++++++++++++++++++++
3 files changed, 60 insertions(+), 1 deletion(-)
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 40264f60b0da..746e18bf8984 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_remove_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 00d272d134c2..76b0d64ce8fa 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -168,9 +168,11 @@ 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 */
+ /* Intended memory leak on "impossible" error */
if (!cc)
kvm_s390_pv_dealloc_vm(kvm);
+ else
+ s390_replace_asce(kvm->arch.gmap);
return cc ? -EIO : 0;
}
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 9bb2c7512cd5..5a138f6220c4 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2706,3 +2706,58 @@ void s390_reset_acc(struct mm_struct *mm)
mmput(mm);
}
EXPORT_SYMBOL_GPL(s390_reset_acc);
+
+/*
+ * Remove the topmost level of page tables from the list of page tables of
+ * the gmap.
+ * This means that it will not be freed when the VM is torn down, and needs
+ * to be handled separately by the caller, unless an intentional leak is
+ * intended.
+ */
+void s390_remove_old_asce(struct gmap *gmap)
+{
+ struct page *old;
+
+ old = virt_to_page(gmap->table);
+ spin_lock(&gmap->guest_table_lock);
+ list_del(&old->lru);
+ spin_unlock(&gmap->guest_table_lock);
+ /* in case the ASCE needs to be "removed" multiple times */
+ INIT_LIST_HEAD(&old->lru);
+}
+EXPORT_SYMBOL_GPL(s390_remove_old_asce);
+
+/*
+ * Try to replace the current ASCE with another equivalent one.
+ * If the allocation of the new top level page table fails, the ASCE is not
+ * replaced.
+ * In any case, the old ASCE is removed from the list, therefore the caller
+ * has to make sure to save a pointer to it beforehands, unless an
+ * intentional leak is intended.
+ */
+int s390_replace_asce(struct gmap *gmap)
+{
+ unsigned long asce;
+ struct page *page;
+ void *table;
+
+ s390_remove_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));
+
+ spin_lock(&gmap->guest_table_lock);
+ list_add(&page->lru, &gmap->crst_list);
+ spin_unlock(&gmap->guest_table_lock);
+
+ asce = (gmap->asce & ~PAGE_MASK) | __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);
--
2.31.1
