x86/vdso: Zap vvar pages when switching to a time namespace

The VVAR page layout depends on whether a task belongs to the root or
non-root time namespace. Whenever a task changes its namespace, the VVAR
page tables are cleared and then they will be re-faulted with a
corresponding layout.

Co-developed-by: Andrei Vagin <[email protected]>
Signed-off-by: Andrei Vagin <[email protected]>
Signed-off-by: Dmitry Safonov <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: 0x7f454c46

arch/x86/entry/vdso/vma.c

@@ -51,6 +51,7 @@ void __init init_vdso_image(const struct vdso_image *image)
 						image->alt_len));
 }
 
+static const struct vm_special_mapping vvar_mapping;
 struct linux_binprm;
 
 static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
@@ -128,6 +129,32 @@ static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
 
 	return NULL;
 }
+
+/*
+ * The vvar page layout depends on whether a task belongs to the root or
+ * non-root time namespace. Whenever a task changes its namespace, the VVAR
+ * page tables are cleared and then they will re-faulted with a
+ * corresponding layout.
+ * See also the comment near timens_setup_vdso_data() for details.
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+
+	if (down_write_killable(&mm->mmap_sem))
+		return -EINTR;
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long size = vma->vm_end - vma->vm_start;
+
+		if (vma_is_special_mapping(vma, &vvar_mapping))
+			zap_page_range(vma, vma->vm_start, size);
+	}
+
+	up_write(&mm->mmap_sem);
+	return 0;
+}
 #else
 static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma)
 {

include/linux/time_namespace.h

@@ -31,6 +31,9 @@ struct time_namespace {
 extern struct time_namespace init_time_ns;
 
 #ifdef CONFIG_TIME_NS
+extern int vdso_join_timens(struct task_struct *task,
+			    struct time_namespace *ns);
+
 static inline struct time_namespace *get_time_ns(struct time_namespace *ns)
 {
 	kref_get(&ns->kref);
@@ -77,6 +80,12 @@ static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim)
 }
 
 #else
+static inline int vdso_join_timens(struct task_struct *task,
+				   struct time_namespace *ns)
+{
+	return 0;
+}
+
 static inline struct time_namespace *get_time_ns(struct time_namespace *ns)
 {
 	return NULL;

kernel/time/namespace.c

@@ -281,6 +281,7 @@ static void timens_put(struct ns_common *ns)
 static int timens_install(struct nsproxy *nsproxy, struct ns_common *new)
 {
 	struct time_namespace *ns = to_time_ns(new);
+	int err;
 
 	if (!current_is_single_threaded())
 		return -EUSERS;
@@ -291,6 +292,10 @@ static int timens_install(struct nsproxy *nsproxy, struct ns_common *new)
 
 	timens_set_vvar_page(current, ns);
 
+	err = vdso_join_timens(current, ns);
+	if (err)
+		return err;
+
 	get_time_ns(ns);
 	put_time_ns(nsproxy->time_ns);
 	nsproxy->time_ns = ns;
@@ -305,13 +310,18 @@ int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk)
 {
 	struct ns_common *nsc = &nsproxy->time_ns_for_children->ns;
 	struct time_namespace *ns = to_time_ns(nsc);
+	int err;
 
 	/* create_new_namespaces() already incremented the ref counter */
 	if (nsproxy->time_ns == nsproxy->time_ns_for_children)
 		return 0;
 
 	timens_set_vvar_page(tsk, ns);
 
+	err = vdso_join_timens(tsk, ns);
+	if (err)
+		return err;
+
 	get_time_ns(ns);
 	put_time_ns(nsproxy->time_ns);
 	nsproxy->time_ns = ns;