execute: support syscall filtering using seccomp filters

6 files changed, 159 insertions, 2 deletions

diff --git a/src/shared/dbus-common.c b/src/shared/dbus-common.c
index 3f5ce97680..7d57680cfc 100644
--- a/src/shared/dbus-common.c
+++ b/src/shared/dbus-common.c
@@ -1083,6 +1083,29 @@ int generic_print_property(const char *name, DBusMessageIter *iter, bool all) {
                         }
 
                         return 1;
+
+                } else if (dbus_message_iter_get_element_type(iter) == DBUS_TYPE_UINT32) {
+                        DBusMessageIter sub;
+
+                        dbus_message_iter_recurse(iter, &sub);
+                        if (all ||
+                            dbus_message_iter_get_arg_type(&sub) != DBUS_TYPE_INVALID) {
+                                printf("%s=", name);
+
+                                while (dbus_message_iter_get_arg_type(&sub) != DBUS_TYPE_INVALID) {
+                                        uint32_t u;
+
+                                        assert(dbus_message_iter_get_arg_type(&sub) == DBUS_TYPE_UINT32);
+                                        dbus_message_iter_get_basic(&sub, &u);
+                                        printf("%08x", u);
+
+                                        dbus_message_iter_next(&sub);
+                                }
+
+                                puts("");
+                        }
+
+                        return 1;
                 }
 
                 break;
diff --git a/src/shared/exit-status.c b/src/shared/exit-status.c
index b07a66a3e2..0dc82b2e13 100644
--- a/src/shared/exit-status.c
+++ b/src/shared/exit-status.c
@@ -122,6 +122,12 @@ const char* exit_status_to_string(ExitStatus status, ExitStatusLevel level) {
 
                 case EXIT_NAMESPACE:
                         return "NAMESPACE";
+
+                case EXIT_NO_NEW_PRIVILEGES:
+                        return "NO_NEW_PRIVILEGES";
+
+                case EXIT_SECCOMP:
+                        return "SECCOMP";
                 }
         }
 
diff --git a/src/shared/exit-status.h b/src/shared/exit-status.h
index 349e24fbf2..813f1ce1b4 100644
--- a/src/shared/exit-status.h
+++ b/src/shared/exit-status.h
@@ -66,8 +66,9 @@ typedef enum ExitStatus {
         EXIT_TCPWRAP,
         EXIT_PAM,
         EXIT_NETWORK,
-        EXIT_NAMESPACE
-
+        EXIT_NAMESPACE,
+        EXIT_NO_NEW_PRIVILEGES,
+        EXIT_SECCOMP
 } ExitStatus;
 
 typedef enum ExitStatusLevel {
diff --git a/src/shared/linux/seccomp-bpf.h b/src/shared/linux/seccomp-bpf.h
new file mode 100644
index 0000000000..1e3d136739
--- /dev/null
+++ b/src/shared/linux/seccomp-bpf.h
@@ -0,0 +1,76 @@
+/*
+ * seccomp example for x86 (32-bit and 64-bit) with BPF macros
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Authors:
+ *  Will Drewry <wad@chromium.org>
+ *  Kees Cook <keescook@chromium.org>
+ *
+ * The code may be used by anyone for any purpose, and can serve as a
+ * starting point for developing applications using mode 2 seccomp.
+ */
+#ifndef _SECCOMP_BPF_H_
+#define _SECCOMP_BPF_H_
+
+#include <stdio.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/prctl.h>
+
+#include <linux/unistd.h>
+#include <linux/audit.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+
+#ifndef SECCOMP_MODE_FILTER
+# define SECCOMP_MODE_FILTER	2 /* uses user-supplied filter. */
+# define SECCOMP_RET_KILL	0x00000000U /* kill the task immediately */
+# define SECCOMP_RET_TRAP	0x00030000U /* disallow and force a SIGSYS */
+# define SECCOMP_RET_ALLOW	0x7fff0000U /* allow */
+struct seccomp_data {
+    int nr;
+    __u32 arch;
+    __u64 instruction_pointer;
+    __u64 args[6];
+};
+#endif
+#ifndef SYS_SECCOMP
+# define SYS_SECCOMP 1
+#endif
+
+#define syscall_nr (offsetof(struct seccomp_data, nr))
+#define arch_nr (offsetof(struct seccomp_data, arch))
+
+#if defined(__i386__)
+# define REG_SYSCALL	REG_EAX
+# define ARCH_NR	AUDIT_ARCH_I386
+#elif defined(__x86_64__)
+# define REG_SYSCALL	REG_RAX
+# define ARCH_NR	AUDIT_ARCH_X86_64
+#else
+# warning "Platform does not support seccomp filter yet"
+# define REG_SYSCALL	0
+# define ARCH_NR	0
+#endif
+
+#define VALIDATE_ARCHITECTURE \
+	BPF_STMT(BPF_LD+BPF_W+BPF_ABS, arch_nr), \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, ARCH_NR, 1, 0), \
+	BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL)
+
+#define EXAMINE_SYSCALL \
+	BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_nr)
+
+#define ALLOW_SYSCALL(name) \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_##name, 0, 1), \
+	BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW)
+
+#define _KILL_PROCESS \
+	BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL)
+
+#endif /* _SECCOMP_BPF_H_ */
diff --git a/src/shared/linux/seccomp.h b/src/shared/linux/seccomp.h
new file mode 100644
index 0000000000..9c03683fa0
--- /dev/null
+++ b/src/shared/linux/seccomp.h
@@ -0,0 +1,47 @@
+#ifndef _LINUX_SECCOMP_H
+#define _LINUX_SECCOMP_H
+
+
+#include <linux/types.h>
+
+
+/* Valid values for seccomp.mode and prctl(PR_SET_SECCOMP, <mode>) */
+#define SECCOMP_MODE_DISABLED	0 /* seccomp is not in use. */
+#define SECCOMP_MODE_STRICT	1 /* uses hard-coded filter. */
+#define SECCOMP_MODE_FILTER	2 /* uses user-supplied filter. */
+
+/*
+ * All BPF programs must return a 32-bit value.
+ * The bottom 16-bits are for optional return data.
+ * The upper 16-bits are ordered from least permissive values to most.
+ *
+ * The ordering ensures that a min_t() over composed return values always
+ * selects the least permissive choice.
+ */
+#define SECCOMP_RET_KILL	0x00000000U /* kill the task immediately */
+#define SECCOMP_RET_TRAP	0x00030000U /* disallow and force a SIGSYS */
+#define SECCOMP_RET_ERRNO	0x00050000U /* returns an errno */
+#define SECCOMP_RET_TRACE	0x7ff00000U /* pass to a tracer or disallow */
+#define SECCOMP_RET_ALLOW	0x7fff0000U /* allow */
+
+/* Masks for the return value sections. */
+#define SECCOMP_RET_ACTION	0x7fff0000U
+#define SECCOMP_RET_DATA	0x0000ffffU
+
+/**
+ * struct seccomp_data - the format the BPF program executes over.
+ * @nr: the system call number
+ * @arch: indicates system call convention as an AUDIT_ARCH_* value
+ *        as defined in <linux/audit.h>.
+ * @instruction_pointer: at the time of the system call.
+ * @args: up to 6 system call arguments always stored as 64-bit values
+ *        regardless of the architecture.
+ */
+struct seccomp_data {
+	int nr;
+	__u32 arch;
+	__u64 instruction_pointer;
+	__u64 args[6];
+};
+
+#endif /* _LINUX_SECCOMP_H */
diff --git a/src/shared/missing.h b/src/shared/missing.h
index 0cf7949d2c..d918c4e9a7 100644
--- a/src/shared/missing.h
+++ b/src/shared/missing.h
@@ -188,4 +188,8 @@ static inline pid_t gettid(void) {
 #define MS_STRICTATIME (1<<24)
 #endif
 
+#ifndef PR_SET_NO_NEW_PRIVS
+#define PR_SET_NO_NEW_PRIVS 38
+#endif
+
 #endif