um: Add seccomp support

This brings SECCOMP_MODE_STRICT and SECCOMP_MODE_FILTER support through
prctl(2) and seccomp(2) to User-mode Linux for i386 and x86_64
subarchitectures.

secure_computing() is called first in handle_syscall() so that the
syscall emulation will be aborted quickly if matching a seccomp rule.

This is inspired from Meredydd Luff's patch
(https://gerrit.chromium.org/gerrit/21425).

Signed-off-by: Mickaël Salaün <mic@digikod.net>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Will Drewry <wad@chromium.org>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Meredydd Luff <meredydd@senatehouse.org>
Cc: David Drysdale <drysdale@google.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
Acked-by: Kees Cook <keescook@chromium.org>

Documentation/features/seccomp/seccomp-filter/arch-support.txt

@@ -33,7 +33,7 @@
     |          sh: | TODO |
     |       sparc: | TODO |
     |        tile: |  ok  |
-    |          um: | TODO |
+    |          um: |  ok  |
     |   unicore32: | TODO |
     |         x86: |  ok  |
     |      xtensa: | TODO |

arch/um/Kconfig.common

@@ -2,6 +2,7 @@ config UML
 	bool
 	default y
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_UID16
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select GENERIC_IRQ_SHOW

arch/um/Kconfig.um

@@ -104,3 +104,19 @@ config PGTABLE_LEVELS
 	int
 	default 3 if 3_LEVEL_PGTABLES
 	default 2
+
+config SECCOMP
+	def_bool y
+	prompt "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.
+
+	  If unsure, say Y.

arch/um/include/asm/thread_info.h

@@ -62,11 +62,13 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_AUDIT	6
 #define TIF_RESTORE_SIGMASK	7
 #define TIF_NOTIFY_RESUME	8
+#define TIF_SECCOMP		9	/* secure computing */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_MEMDIE		(1 << TIF_MEMDIE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 
 #endif

arch/um/kernel/skas/syscall.c

@@ -5,6 +5,7 @@
 
 #include <linux/kernel.h>
 #include <linux/ptrace.h>
+#include <linux/seccomp.h>
 #include <kern_util.h>
 #include <sysdep/ptrace.h>
 #include <sysdep/ptrace_user.h>
@@ -19,6 +20,10 @@ void handle_syscall(struct uml_pt_regs *r)
 	UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp);
 	PT_REGS_SET_SYSCALL_RETURN(regs, -ENOSYS);
 
+	/* Do the secure computing check first; failures should be fast. */
+	if (secure_computing() == -1)
+		return;
+
 	if (syscall_trace_enter(regs))
 		goto out;