linux-kernel - [tip: timers/core] x86/vdso: Zap vvar pages when switching to a time namespace

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <157900693486.396.13799366172237092744.tip-bot2@tip-bot2>
Date:   Tue, 14 Jan 2020 13:02:14 -0000
From:   "tip-bot2 for Dmitry Safonov" <tip-bot2@...utronix.de>
To:     linux-tip-commits@...r.kernel.org
Cc:     Andrei Vagin <avagin@...il.com>, Dmitry Safonov <dima@...sta.com>,
        Thomas Gleixner <tglx@...utronix.de>, x86 <x86@...nel.org>,
        LKML <linux-kernel@...r.kernel.org>
Subject: [tip: timers/core] x86/vdso: Zap vvar pages when switching to a time
 namespace

The following commit has been merged into the timers/core branch of tip:

Commit-ID:     70ddf65184ec1e8989322f35193e4fde7377f0cc
Gitweb:        https://git.kernel.org/tip/70ddf65184ec1e8989322f35193e4fde7377f0cc
Author:        Dmitry Safonov <dima@...sta.com>
AuthorDate:    Tue, 12 Nov 2019 01:27:15 
Committer:     Thomas Gleixner <tglx@...utronix.de>
CommitterDate: Tue, 14 Jan 2020 12:20:59 +01:00

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 <avagin@...il.com>
Signed-off-by: Andrei Vagin <avagin@...il.com>
Signed-off-by: Dmitry Safonov <dima@...sta.com>
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
Link: https://lore.kernel.org/r/20191112012724.250792-27-dima@arista.com


---
 arch/x86/entry/vdso/vma.c      | 27 +++++++++++++++++++++++++++
 include/linux/time_namespace.h |  9 +++++++++
 kernel/time/namespace.c        | 10 ++++++++++
 3 files changed, 46 insertions(+)

diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index d2fd8a5..c1b8496 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/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)
 {
diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index 6b7767f..04a2ba8 100644
--- a/include/linux/time_namespace.h
+++ b/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;
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index d705c15..0732964 100644
--- a/kernel/time/namespace.c
+++ b/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;
@@ -305,6 +310,7 @@ 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)
@@ -312,6 +318,10 @@ int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk)
 
 	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;