@@ -27,6 +27,7 @@ config ARM64
select HARDIRQS_SW_RESEND
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
select HAVE_C_RECORDMCOUNT
select HAVE_DEBUG_BUGVERBOSE
@@ -229,6 +230,19 @@ config HAVE_ARCH_TRANSPARENT_HUGEPAGE
source "mm/Kconfig"
+config SECCOMP
+ bool "Enable seccomp to safely compute untrusted bytecode"
+ ---help---
+ This kernel feature is useful for number crunching applications
+ that may need to compute untrusted bytecode during their
+ execution. By using pipes or other transports made available to
+ the process as file descriptors supporting the read/write
+ syscalls, it's possible to isolate those applications in
+ their own address space using seccomp. Once seccomp is
+ enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
+ and the task is only allowed to execute a few safe syscalls
+ defined by each seccomp mode.
+
config XEN_DOM0
def_bool y
depends on XEN
new file mode 100644
@@ -0,0 +1,25 @@
+/*
+ * arch/arm64/include/asm/seccomp.h
+ *
+ * Copyright (C) 2014 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
+
+#include <asm/unistd.h>
+
+#ifdef CONFIG_COMPAT
+#define __NR_seccomp_read_32 __NR_compat_read
+#define __NR_seccomp_write_32 __NR_compat_write
+#define __NR_seccomp_exit_32 __NR_compat_exit
+#define __NR_seccomp_sigreturn_32 __NR_compat_rt_sigreturn
+#endif /* CONFIG_COMPAT */
+
+#include <asm-generic/seccomp.h>
+
+#endif /* _ASM_SECCOMP_H */
@@ -30,6 +30,9 @@
* Compat syscall numbers used by the AArch64 kernel.
*/
#define __NR_compat_restart_syscall 0
+#define __NR_compat_exit 1
+#define __NR_compat_read 3
+#define __NR_compat_write 4
#define __NR_compat_sigreturn 119
#define __NR_compat_rt_sigreturn 173
@@ -650,6 +650,10 @@ ENDPROC(el0_svc)
__sys_trace:
mov x0, sp
bl syscall_trace_enter
+#ifdef CONFIG_SECCOMP
+ cmp w0, #-EPERM // check seccomp result
+ b.eq ret_to_user // -EPERM means 'rejected'
+#endif
adr lr, __sys_trace_return // return address
uxtw scno, w0 // syscall number (possibly new)
mov x1, sp // pointer to regs
@@ -20,12 +20,14 @@
*/
#include <linux/audit.h>
+#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/ptrace.h>
#include <linux/user.h>
+#include <linux/seccomp.h>
#include <linux/security.h>
#include <linux/init.h>
#include <linux/signal.h>
@@ -1067,6 +1069,10 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs)
{
unsigned long saved_reg;
+ if (secure_computing(regs->syscallno) == -1)
+ /* seccomp failures shouldn't expose any additional code. */
+ return -EPERM;
+
if (test_thread_flag(TIF_SYSCALL_TRACE)) {
/*
* A scrach register (ip(r12) on AArch32, x7 on AArch64) is
secure_computing() should always be called first in syscall_trace_enter(). If it returns non-zero, we should stop further handling. Then that system call may eventually fail, be trapped or the process itself be killed depending on loaded rules. In this case, syscall_trace_enter() returns a dedicated value in order to skip a normal syscall table lookup because a seccomp rule may have already overridden errno. Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org> --- arch/arm64/Kconfig | 14 ++++++++++++++ arch/arm64/include/asm/seccomp.h | 25 +++++++++++++++++++++++++ arch/arm64/include/asm/unistd.h | 3 +++ arch/arm64/kernel/entry.S | 4 ++++ arch/arm64/kernel/ptrace.c | 6 ++++++ 5 files changed, 52 insertions(+) create mode 100644 arch/arm64/include/asm/seccomp.h