[Devel] [PATCH hci-8.1 v2 4/6] timens: freeze the offsets on the first join without the vDSO too

[Eva Kurchatova <eva.kurchatova@virtuozzo.com>]

A time namespace's offsets may be written until the first task joins
it; from then on they are read without a lock, so that join freezes
them. The freeze sat in the code that fills the namespace's vDSO
page, and since 1b6c89285d37 ("timens: Remove dependency on the vDSO")
a kernel without a generic vDSO, User Mode Linux now, never froze: the
owner could rewrite the offsets under the tasks already running there,
and the clocks they read moved with them.

Freeze in timens_commit() itself and fill the vDSO page from there,
where there is one.

Fixes: 1b6c89285d37 ("timens: Remove dependency on the vDSO")
https://virtuozzo.atlassian.net/browse/VSTOR-148112
Feature: fix ms/timens
Signed-off-by: Eva Kurchatova <eva.kurchatova@virtuozzo.com>
---
 include/linux/time_namespace.h   | 11 ++++++-----
 kernel/time/namespace.c          | 28 +++++++++++++++++++++++++++
 kernel/time/namespace_internal.h | 10 ++++++++++
 kernel/time/namespace_vdso.c     | 33 +++++---------------------------
 4 files changed, 49 insertions(+), 33 deletions(-)

diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index e91910656301..bfe55d9066b5 100644
--- a/include/linux/time_namespace.h
+++ b/include/linux/time_namespace.h
@@ -49,6 +49,7 @@ struct time_namespace *copy_time_ns(unsigned long flags,
 				    struct time_namespace *old_ns);
 void free_time_ns(struct time_namespace *ns);
 void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk);
+void timens_commit(struct task_struct *tsk, struct time_namespace *ns);
 
 static inline void put_time_ns(struct time_namespace *ns)
 {
@@ -134,6 +135,11 @@ static inline void timens_on_fork(struct nsproxy *nsproxy,
 	return;
 }
 
+static inline void timens_commit(struct task_struct *tsk,
+				 struct time_namespace *ns)
+{
+}
+
 static inline void timens_add_monotonic(struct timespec64 *ts) { }
 static inline void timens_add_boottime(struct timespec64 *ts) { }
 
@@ -151,13 +157,8 @@ static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim)
 #endif
 
 #ifdef CONFIG_TIME_NS_VDSO
-extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns);
 struct page *find_timens_vvar_page(struct vm_area_struct *vma);
 #else /* !CONFIG_TIME_NS_VDSO */
-static inline void timens_commit(struct task_struct *tsk, struct time_namespace *ns)
-{
-}
-
 static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma)
 {
 	return NULL;
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index cf95f9e0ad94..9bd21eb8bf2d 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -192,6 +192,34 @@ static void timens_put(struct ns_common *ns)
 	put_time_ns(to_time_ns(ns));
 }
 
+/*
+ * The offsets are read without a lock once a task runs in the namespace,
+ * so the first task to join freezes them, and sets up the vDSO page from
+ * them where there is one.
+ */
+static void timens_freeze_offsets(struct time_namespace *ns)
+{
+	if (ns == &init_time_ns)
+		return;
+
+	/* Fast-path, taken by every task in namespace except the first. */
+	if (likely(ns->frozen_offsets))
+		return;
+
+	guard(mutex)(&timens_offset_lock);
+	if (ns->frozen_offsets)
+		return;
+
+	timens_vdso_setup_vvar_page(ns);
+	ns->frozen_offsets = true;
+}
+
+void timens_commit(struct task_struct *tsk, struct time_namespace *ns)
+{
+	timens_freeze_offsets(ns);
+	timens_vdso_join(tsk, ns);
+}
+
 static int timens_install(struct nsset *nsset, struct ns_common *new)
 {
 	struct nsproxy *nsproxy = nsset->nsproxy;
diff --git a/kernel/time/namespace_internal.h b/kernel/time/namespace_internal.h
index b37ba179f43b..564c22b639dc 100644
--- a/kernel/time/namespace_internal.h
+++ b/kernel/time/namespace_internal.h
@@ -4,6 +4,7 @@
 
 #include <linux/mutex.h>
 
+struct task_struct;
 struct time_namespace;
 
 /*
@@ -15,6 +16,8 @@ extern struct mutex timens_offset_lock;
 #ifdef CONFIG_TIME_NS_VDSO
 int timens_vdso_alloc_vvar_page(struct time_namespace *ns);
 void timens_vdso_free_vvar_page(struct time_namespace *ns);
+void timens_vdso_setup_vvar_page(struct time_namespace *ns);
+void timens_vdso_join(struct task_struct *task, struct time_namespace *ns);
 #else /* !CONFIG_TIME_NS_VDSO */
 static inline int timens_vdso_alloc_vvar_page(struct time_namespace *ns)
 {
@@ -23,6 +26,13 @@ static inline int timens_vdso_alloc_vvar_page(struct time_namespace *ns)
 static inline void timens_vdso_free_vvar_page(struct time_namespace *ns)
 {
 }
+static inline void timens_vdso_setup_vvar_page(struct time_namespace *ns)
+{
+}
+static inline void timens_vdso_join(struct task_struct *task,
+				    struct time_namespace *ns)
+{
+}
 #endif /* CONFIG_TIME_NS_VDSO */
 
 #endif /* _TIME_NAMESPACE_INTERNAL_H */
diff --git a/kernel/time/namespace_vdso.c b/kernel/time/namespace_vdso.c
index 08d69270eb2c..8a2fc9d23687 100644
--- a/kernel/time/namespace_vdso.c
+++ b/kernel/time/namespace_vdso.c
@@ -86,29 +86,13 @@ struct page *find_timens_vvar_page(struct vm_area_struct *vma)
 	return NULL;
 }
 
-static void timens_set_vvar_page(struct task_struct *task,
-				struct time_namespace *ns)
+/* Called once per namespace, under timens_offset_lock, before any task reads */
+void timens_vdso_setup_vvar_page(struct time_namespace *ns)
 {
-	struct vdso_time_data *vdata;
-	struct vdso_clock *vc;
+	struct vdso_time_data *vdata = page_address(ns->vvar_page);
+	struct vdso_clock *vc = vdata->clock_data;
 	unsigned int i;
 
-	if (ns == &init_time_ns)
-		return;
-
-	/* Fast-path, taken by every task in namespace except the first. */
-	if (likely(ns->frozen_offsets))
-		return;
-
-	guard(mutex)(&timens_offset_lock);
-	/* Nothing to-do: vvar_page has been already initialized. */
-	if (ns->frozen_offsets)
-		return;
-
-	ns->frozen_offsets = true;
-	vdata = page_address(ns->vvar_page);
-	vc = vdata->clock_data;
-
 	for (i = 0; i < CS_BASES; i++)
 		timens_setup_vdso_clock_data(&vc[i], ns);
 }
@@ -120,7 +104,7 @@ static void timens_set_vvar_page(struct task_struct *task,
  * corresponding layout.
  * See also the comment near timens_setup_vdso_clock_data() for details.
  */
-static int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+void timens_vdso_join(struct task_struct *task, struct time_namespace *ns)
 {
 	struct mm_struct *mm = task->mm;
 	struct vm_area_struct *vma;
@@ -131,13 +115,6 @@ static int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 		if (vma_is_special_mapping(vma, &vdso_vvar_mapping))
 			zap_vma_pages(vma);
 	}
-	return 0;
-}
-
-void timens_commit(struct task_struct *tsk, struct time_namespace *ns)
-{
-	timens_set_vvar_page(tsk, ns);
-	vdso_join_timens(tsk, ns);
 }
 
 int timens_vdso_alloc_vvar_page(struct time_namespace *ns)
-- 
2.56.0

_______________________________________________
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel