linux-kernel - [PATCHv3 16/27] x86/vdso: Switch image on setns()/unshare()/clone()

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: <20190425161416.26600-17-dima@arista.com>
Date:   Thu, 25 Apr 2019 17:14:05 +0100
From:   Dmitry Safonov <dima@...sta.com>
To:     linux-kernel@...r.kernel.org
Cc:     Dmitry Safonov <dima@...sta.com>, Adrian Reber <adrian@...as.de>,
        Andrei Vagin <avagin@...nvz.org>,
        Andy Lutomirski <luto@...nel.org>,
        Arnd Bergmann <arnd@...db.de>,
        Christian Brauner <christian.brauner@...ntu.com>,
        Cyrill Gorcunov <gorcunov@...nvz.org>,
        Dmitry Safonov <0x7f454c46@...il.com>,
        "Eric W. Biederman" <ebiederm@...ssion.com>,
        "H. Peter Anvin" <hpa@...or.com>, Ingo Molnar <mingo@...hat.com>,
        Jeff Dike <jdike@...toit.com>, Oleg Nesterov <oleg@...hat.com>,
        Pavel Emelyanov <xemul@...tuozzo.com>,
        Shuah Khan <shuah@...nel.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Vincenzo Frascino <vincenzo.frascino@....com>,
        containers@...ts.linux-foundation.org, criu@...nvz.org,
        linux-api@...r.kernel.org, x86@...nel.org,
        Andrei Vagin <avagin@...il.com>
Subject: [PATCHv3 16/27] x86/vdso: Switch image on setns()/unshare()/clone()

As it has been discussed on timens RFC, adding a new conditional branch
`if (inside_time_ns)` on VDSO for all processes is undesirable.
It will add a penalty for everybody as branch predictor may mispredict
the jump. Also there are instruction cache lines wasted on cmp/jmp.

Those effects of introducing time namespace are very much unwanted
having in mind how much work have been spent on micro-optimisation
vdso code.

Addressing those problems, there are two versions of VDSO's .so:
for host tasks (without any penalty) and for processes inside of time
namespace with clk_to_ns() that subtracts offsets from host's time.

Whenever a user does setns()/unshare() or clone() with CLONE_TIMENS,
change VDSO image in mm and zap existing VVAR/VDSO page tables.
They will be re-faulted with corresponding image and VVAR offsets.

Co-developed-by: Andrei Vagin <avagin@...il.com>
Signed-off-by: Andrei Vagin <avagin@...il.com>
Signed-off-by: Dmitry Safonov <dima@...sta.com>
---
 arch/x86/entry/vdso/vma.c   | 29 +++++++++++++++++++++++++++++
 arch/x86/include/asm/vdso.h |  1 +
 kernel/time_namespace.c     | 11 +++++++++++
 3 files changed, 41 insertions(+)

diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 6aae9c0d400d..28628950214d 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -25,6 +25,7 @@
 #include <asm/cpufeature.h>
 #include <asm/mshyperv.h>
 #include <asm/page.h>
+#include <asm/tlb.h>
 
 #if defined(CONFIG_X86_64)
 unsigned int __read_mostly vdso64_enabled = 1;
@@ -189,6 +190,34 @@ static const struct vm_special_mapping vvar_mapping = {
 	.mremap = vvar_mremap,
 };
 
+#ifdef CONFIG_TIME_NS
+int vdso_join_timens(struct task_struct *task, bool inside_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);
+		if (vma_is_special_mapping(vma, &vdso_mapping))
+			zap_page_range(vma, vma->vm_start, size);
+	}
+
+	up_write(&mm->mmap_sem);
+	return 0;
+}
+#else /* CONFIG_TIME_NS */
+int vdso_join_timens(struct task_struct *task, bool inside_ns)
+{
+	return -ENXIO;
+}
+#endif
+
 /*
  * Add vdso and vvar mappings to current process.
  * @image          - blob to map
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index a620c7f23425..583133446874 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -46,6 +46,7 @@ extern struct vdso_image vdso_image_32;
 extern void __init init_vdso_image(struct vdso_image *image);
 
 extern int map_vdso_once(const struct vdso_image *image, unsigned long addr);
+extern int vdso_join_timens(struct task_struct *task, bool inside_ns);
 
 #endif /* __ASSEMBLER__ */
 
diff --git a/kernel/time_namespace.c b/kernel/time_namespace.c
index 4828447721ec..e806accc4eaf 100644
--- a/kernel/time_namespace.c
+++ b/kernel/time_namespace.c
@@ -14,6 +14,7 @@
 #include <linux/proc_ns.h>
 #include <linux/sched/task.h>
 #include <linux/mm.h>
+#include <asm/vdso.h>
 
 static struct ucounts *inc_time_namespaces(struct user_namespace *ns)
 {
@@ -155,11 +156,16 @@ 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 ret;
 
 	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
 	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
 		return -EPERM;
 
+	ret = vdso_join_timens(current, ns != &init_time_ns);
+	if (ret)
+		return ret;
+
 	get_time_ns(ns);
 	get_time_ns(ns);
 	put_time_ns(nsproxy->time_ns);
@@ -174,10 +180,15 @@ 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 ret;
 
 	if (nsproxy->time_ns == nsproxy->time_ns_for_children)
 		return 0;
 
+	ret = vdso_join_timens(tsk, ns != &init_time_ns);
+	if (ret)
+		return ret;
+
 	get_time_ns(ns);
 	put_time_ns(nsproxy->time_ns);
 	nsproxy->time_ns = ns;
-- 
2.21.0