arm64/vdso: Zap vvar pages when switching to a time namespace

The order of vvar pages depends on whether a task belongs to the root
time namespace or not. In the root time namespace, a task doesn't have a
per-namespace page. In a non-root namespace, the VVAR page which contains
the system-wide VDSO data is replaced with a namespace specific page
that contains clock offsets.

Whenever a task changes its namespace, the VVAR page tables are cleared
and then they will be re-faulted with a corresponding layout.

A task can switch its time namespace only if its ->mm isn't shared with
another task.
Signed-off-by: Andrei Vagin <avagin@gmail.com>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Dmitry Safonov <dima@arista.com>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20200624083321.144975-3-avagin@gmail.comSigned-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/kernel/vdso.c

@@ -124,6 +124,37 @@ static int __vdso_init(enum vdso_abi abi)
 	return 0;
 }
 
+#ifdef CONFIG_TIME_NS
+/*
+ * The vvar mapping contains data for a specific time namespace, so when a task
+ * changes namespace we must unmap its vvar data for the old namespace.
+ * Subsequent faults will map in data for the new namespace.
+ *
+ * For more details see timens_setup_vdso_data().
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+
+	mmap_read_lock(mm);
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long size = vma->vm_end - vma->vm_start;
+
+		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA64].dm))
+			zap_page_range(vma, vma->vm_start, size);
+#ifdef CONFIG_COMPAT_VDSO
+		if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA32].dm))
+			zap_page_range(vma, vma->vm_start, size);
+#endif
+	}
+
+	mmap_read_unlock(mm);
+	return 0;
+}
+#endif
+
 static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 			     struct vm_area_struct *vma, struct vm_fault *vmf)
 {