Merge tag 'seccomp-v4.14-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull seccomp updates from Kees Cook:
 "Major additions:

   - sysctl and seccomp operation to discover available actions
     (tyhicks)

   - new per-filter configurable logging infrastructure and sysctl
     (tyhicks)

   - SECCOMP_RET_LOG to log allowed syscalls (tyhicks)

   - SECCOMP_RET_KILL_PROCESS as the new strictest possible action

   - self-tests for new behaviors"

[ This is the seccomp part of the security pull request during the merge
  window that was nixed due to unrelated problems   - Linus ]

* tag 'seccomp-v4.14-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  samples: Unrename SECCOMP_RET_KILL
  selftests/seccomp: Test thread vs process killing
  seccomp: Implement SECCOMP_RET_KILL_PROCESS action
  seccomp: Introduce SECCOMP_RET_KILL_PROCESS
  seccomp: Rename SECCOMP_RET_KILL to SECCOMP_RET_KILL_THREAD
  seccomp: Action to log before allowing
  seccomp: Filter flag to log all actions except SECCOMP_RET_ALLOW
  seccomp: Selftest for detection of filter flag support
  seccomp: Sysctl to configure actions that are allowed to be logged
  seccomp: Operation for checking if an action is available
  seccomp: Sysctl to display available actions
  seccomp: Provide matching filter for introspection
  selftests/seccomp: Refactor RET_ERRNO tests
  selftests/seccomp: Add simple seccomp overhead benchmark
  selftests/seccomp: Add tests for basic ptrace actions

Documentation/networking/filter.txt

@@ -337,7 +337,7 @@ Examples for low-level BPF:
   jeq #14, good           /* __NR_rt_sigprocmask */
   jeq #13, good           /* __NR_rt_sigaction */
   jeq #35, good           /* __NR_nanosleep */
-  bad: ret #0             /* SECCOMP_RET_KILL */
+  bad: ret #0             /* SECCOMP_RET_KILL_THREAD */
   good: ret #0x7fff0000   /* SECCOMP_RET_ALLOW */
 
 The above example code can be placed into a file (here called "foo"), and

Documentation/sysctl/kernel.txt

@@ -75,6 +75,7 @@ show up in /proc/sys/kernel:
 - reboot-cmd                  [ SPARC only ]
 - rtsig-max
 - rtsig-nr
+- seccomp/                    ==> Documentation/userspace-api/seccomp_filter.rst
 - sem
 - sem_next_id		      [ sysv ipc ]
 - sg-big-buff                 [ generic SCSI device (sg) ]

Documentation/userspace-api/seccomp_filter.rst

@@ -87,11 +87,16 @@ Return values
 A seccomp filter may return any of the following values. If multiple
 filters exist, the return value for the evaluation of a given system
 call will always use the highest precedent value. (For example,
-``SECCOMP_RET_KILL`` will always take precedence.)
+``SECCOMP_RET_KILL_PROCESS`` will always take precedence.)
 
 In precedence order, they are:
 
-``SECCOMP_RET_KILL``:
+``SECCOMP_RET_KILL_PROCESS``:
+	Results in the entire process exiting immediately without executing
+	the system call.  The exit status of the task (``status & 0x7f``)
+	will be ``SIGSYS``, not ``SIGKILL``.
+
+``SECCOMP_RET_KILL_THREAD``:
 	Results in the task exiting immediately without executing the
 	system call.  The exit status of the task (``status & 0x7f``) will
 	be ``SIGSYS``, not ``SIGKILL``.
@@ -141,6 +146,15 @@ In precedence order, they are:
 	allow use of ptrace, even of other sandboxed processes, without
 	extreme care; ptracers can use this mechanism to escape.)
 
+``SECCOMP_RET_LOG``:
+	Results in the system call being executed after it is logged. This
+	should be used by application developers to learn which syscalls their
+	application needs without having to iterate through multiple test and
+	development cycles to build the list.
+
+	This action will only be logged if "log" is present in the
+	actions_logged sysctl string.
+
 ``SECCOMP_RET_ALLOW``:
 	Results in the system call being executed.
 
@@ -169,7 +183,41 @@ The ``samples/seccomp/`` directory contains both an x86-specific example
 and a more generic example of a higher level macro interface for BPF
 program generation.
 
+Sysctls
+=======
 
+Seccomp's sysctl files can be found in the ``/proc/sys/kernel/seccomp/``
+directory. Here's a description of each file in that directory:
+
+``actions_avail``:
+	A read-only ordered list of seccomp return values (refer to the
+	``SECCOMP_RET_*`` macros above) in string form. The ordering, from
+	left-to-right, is the least permissive return value to the most
+	permissive return value.
+
+	The list represents the set of seccomp return values supported
+	by the kernel. A userspace program may use this list to
+	determine if the actions found in the ``seccomp.h``, when the
+	program was built, differs from the set of actions actually
+	supported in the current running kernel.
+
+``actions_logged``:
+	A read-write ordered list of seccomp return values (refer to the
+	``SECCOMP_RET_*`` macros above) that are allowed to be logged. Writes
+	to the file do not need to be in ordered form but reads from the file
+	will be ordered in the same way as the actions_avail sysctl.
+
+	It is important to note that the value of ``actions_logged`` does not
+	prevent certain actions from being logged when the audit subsystem is
+	configured to audit a task. If the action is not found in
+	``actions_logged`` list, the final decision on whether to audit the
+	action for that task is ultimately left up to the audit subsystem to
+	decide for all seccomp return values other than ``SECCOMP_RET_ALLOW``.
+
+	The ``allow`` string is not accepted in the ``actions_logged`` sysctl
+	as it is not possible to log ``SECCOMP_RET_ALLOW`` actions. Attempting
+	to write ``allow`` to the sysctl will result in an EINVAL being
+	returned.
 
 Adding architecture support
 ===========================

include/linux/audit.h

@@ -314,11 +314,7 @@ void audit_core_dumps(long signr);
 
 static inline void audit_seccomp(unsigned long syscall, long signr, int code)
 {
-	if (!audit_enabled)
-		return;
-
-	/* Force a record to be reported if a signal was delivered. */
-	if (signr || unlikely(!audit_dummy_context()))
+	if (audit_enabled && unlikely(!audit_dummy_context()))
 		__audit_seccomp(syscall, signr, code);
 }
 

include/linux/seccomp.h

@@ -3,7 +3,8 @@
 
 #include <uapi/linux/seccomp.h>
 
-#define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC)
+#define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC | \
+					 SECCOMP_FILTER_FLAG_LOG)
 
 #ifdef CONFIG_SECCOMP
 

include/uapi/linux/seccomp.h

@@ -13,25 +13,32 @@
 /* Valid operations for seccomp syscall. */
 #define SECCOMP_SET_MODE_STRICT		0
 #define SECCOMP_SET_MODE_FILTER		1
+#define SECCOMP_GET_ACTION_AVAIL	2
 
 /* Valid flags for SECCOMP_SET_MODE_FILTER */
 #define SECCOMP_FILTER_FLAG_TSYNC	1
+#define SECCOMP_FILTER_FLAG_LOG		2
 
 /*
  * 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 upper 16-bits are ordered from least permissive values to most,
+ * as a signed value (so 0x8000000 is negative).
  *
  * 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_KILL_PROCESS 0x80000000U /* kill the process */
+#define SECCOMP_RET_KILL_THREAD	 0x00000000U /* kill the thread */
+#define SECCOMP_RET_KILL	 SECCOMP_RET_KILL_THREAD
 #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_LOG		 0x7ffc0000U /* allow after logging */
 #define SECCOMP_RET_ALLOW	 0x7fff0000U /* allow */
 
 /* Masks for the return value sections. */
+#define SECCOMP_RET_ACTION_FULL	0xffff0000U
 #define SECCOMP_RET_ACTION	0x7fff0000U
 #define SECCOMP_RET_DATA	0x0000ffffU
 

kernel/seccomp.c

@@ -17,11 +17,13 @@
 #include <linux/audit.h>
 #include <linux/compat.h>
 #include <linux/coredump.h>
+#include <linux/kmemleak.h>
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 #include <linux/seccomp.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
+#include <linux/sysctl.h>
 
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
 #include <asm/syscall.h>
@@ -42,6 +44,7 @@
  *         get/put helpers should be used when accessing an instance
  *         outside of a lifetime-guarded section.  In general, this
  *         is only needed for handling filters shared across tasks.
+ * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged
  * @prev: points to a previously installed, or inherited, filter
  * @prog: the BPF program to evaluate
  *
@@ -57,6 +60,7 @@
  */
 struct seccomp_filter {
 	refcount_t usage;
+	bool log;
 	struct seccomp_filter *prev;
 	struct bpf_prog *prog;
 };
@@ -171,10 +175,15 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
 /**
  * seccomp_run_filters - evaluates all seccomp filters against @sd
  * @sd: optional seccomp data to be passed to filters
+ * @match: stores struct seccomp_filter that resulted in the return value,
+ *         unless filter returned SECCOMP_RET_ALLOW, in which case it will
+ *         be unchanged.
  *
  * Returns valid seccomp BPF response codes.
  */
-static u32 seccomp_run_filters(const struct seccomp_data *sd)
+#define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL)))
+static u32 seccomp_run_filters(const struct seccomp_data *sd,
+			       struct seccomp_filter **match)
 {
 	struct seccomp_data sd_local;
 	u32 ret = SECCOMP_RET_ALLOW;
@@ -184,7 +193,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd)
 
 	/* Ensure unexpected behavior doesn't result in failing open. */
 	if (unlikely(WARN_ON(f == NULL)))
-		return SECCOMP_RET_KILL;
+		return SECCOMP_RET_KILL_PROCESS;
 
 	if (!sd) {
 		populate_seccomp_data(&sd_local);
@@ -198,8 +207,10 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd)
 	for (; f; f = f->prev) {
 		u32 cur_ret = BPF_PROG_RUN(f->prog, sd);
 
-		if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
+		if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) {
 			ret = cur_ret;
+			*match = f;
+		}
 	}
 	return ret;
 }
@@ -444,6 +455,10 @@ static long seccomp_attach_filter(unsigned int flags,
 			return ret;
 	}
 
+	/* Set log flag, if present. */
+	if (flags & SECCOMP_FILTER_FLAG_LOG)
+		filter->log = true;
+
 	/*
 	 * If there is an existing filter, make it the prev and don't drop its
 	 * task reference.
@@ -514,6 +529,65 @@ static void seccomp_send_sigsys(int syscall, int reason)
 }
 #endif	/* CONFIG_SECCOMP_FILTER */
 
+/* For use with seccomp_actions_logged */
+#define SECCOMP_LOG_KILL_PROCESS	(1 << 0)
+#define SECCOMP_LOG_KILL_THREAD		(1 << 1)
+#define SECCOMP_LOG_TRAP		(1 << 2)
+#define SECCOMP_LOG_ERRNO		(1 << 3)
+#define SECCOMP_LOG_TRACE		(1 << 4)
+#define SECCOMP_LOG_LOG			(1 << 5)
+#define SECCOMP_LOG_ALLOW		(1 << 6)
+
+static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_PROCESS |
+				    SECCOMP_LOG_KILL_THREAD  |
+				    SECCOMP_LOG_TRAP  |
+				    SECCOMP_LOG_ERRNO |
+				    SECCOMP_LOG_TRACE |
+				    SECCOMP_LOG_LOG;
+
+static inline void seccomp_log(unsigned long syscall, long signr, u32 action,
+			       bool requested)
+{
+	bool log = false;
+
+	switch (action) {
+	case SECCOMP_RET_ALLOW:
+		break;
+	case SECCOMP_RET_TRAP:
+		log = requested && seccomp_actions_logged & SECCOMP_LOG_TRAP;
+		break;
+	case SECCOMP_RET_ERRNO:
+		log = requested && seccomp_actions_logged & SECCOMP_LOG_ERRNO;
+		break;
+	case SECCOMP_RET_TRACE:
+		log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE;
+		break;
+	case SECCOMP_RET_LOG:
+		log = seccomp_actions_logged & SECCOMP_LOG_LOG;
+		break;
+	case SECCOMP_RET_KILL_THREAD:
+		log = seccomp_actions_logged & SECCOMP_LOG_KILL_THREAD;
+		break;
+	case SECCOMP_RET_KILL_PROCESS:
+	default:
+		log = seccomp_actions_logged & SECCOMP_LOG_KILL_PROCESS;
+	}
+
+	/*
+	 * Force an audit message to be emitted when the action is RET_KILL_*,
+	 * RET_LOG, or the FILTER_FLAG_LOG bit was set and the action is
+	 * allowed to be logged by the admin.
+	 */
+	if (log)
+		return __audit_seccomp(syscall, signr, action);
+
+	/*
+	 * Let the audit subsystem decide if the action should be audited based
+	 * on whether the current task itself is being audited.
+	 */
+	return audit_seccomp(syscall, signr, action);
+}
+
 /*
  * Secure computing mode 1 allows only read/write/exit/sigreturn.
  * To be fully secure this must be combined with rlimit
@@ -539,7 +613,7 @@ static void __secure_computing_strict(int this_syscall)
 #ifdef SECCOMP_DEBUG
 	dump_stack();
 #endif
-	audit_seccomp(this_syscall, SIGKILL, SECCOMP_RET_KILL);
+	seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL_THREAD, true);
 	do_exit(SIGKILL);
 }
 
@@ -566,6 +640,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 			    const bool recheck_after_trace)
 {
 	u32 filter_ret, action;
+	struct seccomp_filter *match = NULL;
 	int data;
 
 	/*
@@ -574,9 +649,9 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 	 */
 	rmb();
 
-	filter_ret = seccomp_run_filters(sd);
+	filter_ret = seccomp_run_filters(sd, &match);
 	data = filter_ret & SECCOMP_RET_DATA;
-	action = filter_ret & SECCOMP_RET_ACTION;
+	action = filter_ret & SECCOMP_RET_ACTION_FULL;
 
 	switch (action) {
 	case SECCOMP_RET_ERRNO:
@@ -637,14 +712,25 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 
 		return 0;
 
+	case SECCOMP_RET_LOG:
+		seccomp_log(this_syscall, 0, action, true);
+		return 0;
+
 	case SECCOMP_RET_ALLOW:
+		/*
+		 * Note that the "match" filter will always be NULL for
+		 * this action since SECCOMP_RET_ALLOW is the starting
+		 * state in seccomp_run_filters().
+		 */
 		return 0;
 
-	case SECCOMP_RET_KILL:
+	case SECCOMP_RET_KILL_THREAD:
+	case SECCOMP_RET_KILL_PROCESS:
 	default:
-		audit_seccomp(this_syscall, SIGSYS, action);
+		seccomp_log(this_syscall, SIGSYS, action, true);
 		/* Dump core only if this is the last remaining thread. */
-		if (get_nr_threads(current) == 1) {
+		if (action == SECCOMP_RET_KILL_PROCESS ||
+		    get_nr_threads(current) == 1) {
 			siginfo_t info;
 
 			/* Show the original registers in the dump. */
@@ -653,13 +739,16 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 			seccomp_init_siginfo(&info, this_syscall, data);
 			do_coredump(&info);
 		}
+		if (action == SECCOMP_RET_KILL_PROCESS)
+			do_group_exit(SIGSYS);
+		else
 			do_exit(SIGSYS);
 	}
 
 	unreachable();
 
 skip:
-	audit_seccomp(this_syscall, 0, action);
+	seccomp_log(this_syscall, 0, action, match ? match->log : false);
 	return -1;
 }
 #else
@@ -794,6 +883,29 @@ static inline long seccomp_set_mode_filter(unsigned int flags,
 }
 #endif
 
+static long seccomp_get_action_avail(const char __user *uaction)
+{
+	u32 action;
+
+	if (copy_from_user(&action, uaction, sizeof(action)))
+		return -EFAULT;
+
+	switch (action) {
+	case SECCOMP_RET_KILL_PROCESS:
+	case SECCOMP_RET_KILL_THREAD:
+	case SECCOMP_RET_TRAP:
+	case SECCOMP_RET_ERRNO:
+	case SECCOMP_RET_TRACE:
+	case SECCOMP_RET_LOG:
+	case SECCOMP_RET_ALLOW:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 /* Common entry point for both prctl and syscall. */
 static long do_seccomp(unsigned int op, unsigned int flags,
 		       const char __user *uargs)
@@ -805,6 +917,11 @@ static long do_seccomp(unsigned int op, unsigned int flags,
 		return seccomp_set_mode_strict();
 	case SECCOMP_SET_MODE_FILTER:
 		return seccomp_set_mode_filter(flags, uargs);
+	case SECCOMP_GET_ACTION_AVAIL:
+		if (flags != 0)
+			return -EINVAL;
+
+		return seccomp_get_action_avail(uargs);
 	default:
 		return -EINVAL;
 	}
@@ -922,3 +1039,185 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off,
 	return ret;
 }
 #endif
+
+#ifdef CONFIG_SYSCTL
+
+/* Human readable action names for friendly sysctl interaction */
+#define SECCOMP_RET_KILL_PROCESS_NAME	"kill_process"
+#define SECCOMP_RET_KILL_THREAD_NAME	"kill_thread"
+#define SECCOMP_RET_TRAP_NAME		"trap"
+#define SECCOMP_RET_ERRNO_NAME		"errno"
+#define SECCOMP_RET_TRACE_NAME		"trace"
+#define SECCOMP_RET_LOG_NAME		"log"
+#define SECCOMP_RET_ALLOW_NAME		"allow"
+
+static const char seccomp_actions_avail[] =
+				SECCOMP_RET_KILL_PROCESS_NAME	" "
+				SECCOMP_RET_KILL_THREAD_NAME	" "
+				SECCOMP_RET_TRAP_NAME		" "
+				SECCOMP_RET_ERRNO_NAME		" "
+				SECCOMP_RET_TRACE_NAME		" "
+				SECCOMP_RET_LOG_NAME		" "
+				SECCOMP_RET_ALLOW_NAME;
+
+struct seccomp_log_name {
+	u32		log;
+	const char	*name;
+};
+
+static const struct seccomp_log_name seccomp_log_names[] = {
+	{ SECCOMP_LOG_KILL_PROCESS, SECCOMP_RET_KILL_PROCESS_NAME },
+	{ SECCOMP_LOG_KILL_THREAD, SECCOMP_RET_KILL_THREAD_NAME },
+	{ SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME },
+	{ SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME },
+	{ SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME },
+	{ SECCOMP_LOG_LOG, SECCOMP_RET_LOG_NAME },
+	{ SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME },
+	{ }
+};
+
+static bool seccomp_names_from_actions_logged(char *names, size_t size,
+					      u32 actions_logged)
+{
+	const struct seccomp_log_name *cur;
+	bool append_space = false;
+
+	for (cur = seccomp_log_names; cur->name && size; cur++) {
+		ssize_t ret;
+
+		if (!(actions_logged & cur->log))
+			continue;
+
+		if (append_space) {
+			ret = strscpy(names, " ", size);
+			if (ret < 0)
+				return false;
+
+			names += ret;
+			size -= ret;
+		} else
+			append_space = true;
+
+		ret = strscpy(names, cur->name, size);
+		if (ret < 0)
+			return false;
+
+		names += ret;
+		size -= ret;
+	}
+
+	return true;
+}
+
+static bool seccomp_action_logged_from_name(u32 *action_logged,
+					    const char *name)
+{
+	const struct seccomp_log_name *cur;
+
+	for (cur = seccomp_log_names; cur->name; cur++) {
+		if (!strcmp(cur->name, name)) {
+			*action_logged = cur->log;
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names)
+{
+	char *name;
+
+	*actions_logged = 0;
+	while ((name = strsep(&names, " ")) && *name) {
+		u32 action_logged = 0;
+
+		if (!seccomp_action_logged_from_name(&action_logged, name))
+			return false;
+
+		*actions_logged |= action_logged;
+	}
+
+	return true;
+}
+
+static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write,
+					  void __user *buffer, size_t *lenp,
+					  loff_t *ppos)
+{
+	char names[sizeof(seccomp_actions_avail)];
+	struct ctl_table table;
+	int ret;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	memset(names, 0, sizeof(names));
+
+	if (!write) {
+		if (!seccomp_names_from_actions_logged(names, sizeof(names),
+						       seccomp_actions_logged))
+			return -EINVAL;
+	}
+
+	table = *ro_table;
+	table.data = names;
+	table.maxlen = sizeof(names);
+	ret = proc_dostring(&table, write, buffer, lenp, ppos);
+	if (ret)
+		return ret;
+
+	if (write) {
+		u32 actions_logged;
+
+		if (!seccomp_actions_logged_from_names(&actions_logged,
+						       table.data))
+			return -EINVAL;
+
+		if (actions_logged & SECCOMP_LOG_ALLOW)
+			return -EINVAL;
+
+		seccomp_actions_logged = actions_logged;
+	}
+
+	return 0;
+}
+
+static struct ctl_path seccomp_sysctl_path[] = {
+	{ .procname = "kernel", },
+	{ .procname = "seccomp", },
+	{ }
+};
+
+static struct ctl_table seccomp_sysctl_table[] = {
+	{
+		.procname	= "actions_avail",
+		.data		= (void *) &seccomp_actions_avail,
+		.maxlen		= sizeof(seccomp_actions_avail),
+		.mode		= 0444,
+		.proc_handler	= proc_dostring,
+	},
+	{
+		.procname	= "actions_logged",
+		.mode		= 0644,
+		.proc_handler	= seccomp_actions_logged_handler,
+	},
+	{ }
+};
+
+static int __init seccomp_sysctl_init(void)
+{
+	struct ctl_table_header *hdr;
+
+	hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table);
+	if (!hdr)
+		pr_warn("seccomp: sysctl registration failed\n");
+	else
+		kmemleak_not_leak(hdr);
+
+	return 0;
+}
+
+device_initcall(seccomp_sysctl_init)
+
+#endif /* CONFIG_SYSCTL */

tools/testing/selftests/seccomp/Makefile

-TEST_GEN_PROGS := seccomp_bpf
-CFLAGS += -Wl,-no-as-needed -Wall
-LDFLAGS += -lpthread
+all:
 
 include ../lib.mk
 
-$(TEST_GEN_PROGS): seccomp_bpf.c ../kselftest_harness.h
-	$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+.PHONY: all clean
+
+BINARIES := seccomp_bpf seccomp_benchmark
+CFLAGS += -Wl,-no-as-needed -Wall
+
+seccomp_bpf: seccomp_bpf.c ../kselftest_harness.h
+	$(CC) $(CFLAGS) $(LDFLAGS) -lpthread $< -o $@
+
+TEST_PROGS += $(BINARIES)
+EXTRA_CLEAN := $(BINARIES)
+
+all: $(BINARIES)

tools/testing/selftests/seccomp/seccomp_benchmark.c

+/*
+ * Strictly speaking, this is not a test. But it can report during test
+ * runs so relative performace can be measured.
+ */
+#define _GNU_SOURCE
+#include <assert.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <unistd.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+
+#define ARRAY_SIZE(a)    (sizeof(a) / sizeof(a[0]))
+
+unsigned long long timing(clockid_t clk_id, unsigned long long samples)
+{
+	pid_t pid, ret;
+	unsigned long long i;
+	struct timespec start, finish;
+
+	pid = getpid();
+	assert(clock_gettime(clk_id, &start) == 0);
+	for (i = 0; i < samples; i++) {
+		ret = syscall(__NR_getpid);
+		assert(pid == ret);
+	}
+	assert(clock_gettime(clk_id, &finish) == 0);
+
+	i = finish.tv_sec - start.tv_sec;
+	i *= 1000000000;
+	i += finish.tv_nsec - start.tv_nsec;
+
+	printf("%lu.%09lu - %lu.%09lu = %llu\n",
+		finish.tv_sec, finish.tv_nsec,
+		start.tv_sec, start.tv_nsec,
+		i);
+
+	return i;
+}
+
+unsigned long long calibrate(void)
+{
+	unsigned long long i;
+
+	printf("Calibrating reasonable sample size...\n");
+
+	for (i = 5; ; i++) {
+		unsigned long long samples = 1 << i;
+
+		/* Find something that takes more than 5 seconds to run. */
+		if (timing(CLOCK_REALTIME, samples) / 1000000000ULL > 5)
+			return samples;
+	}
+}
+
+int main(int argc, char *argv[])
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog = {
+		.len = (unsigned short)ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+	long ret;
+	unsigned long long samples;
+	unsigned long long native, filtered;
+
+	if (argc > 1)
+		samples = strtoull(argv[1], NULL, 0);
+	else
+		samples = calibrate();
+
+	printf("Benchmarking %llu samples...\n", samples);
+
+	native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+	printf("getpid native: %llu ns\n", native);
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	assert(ret == 0);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+	assert(ret == 0);
+
+	filtered = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+	printf("getpid RET_ALLOW: %llu ns\n", filtered);
+
+	printf("Estimated seccomp overhead per syscall: %llu ns\n",
+		filtered - native);
+
+	if (filtered == native)
+		printf("Trying running again with more samples.\n");
+
+	return 0;
+}

tools/testing/selftests/seccomp/seccomp_bpf.c

@@ -68,23 +68,77 @@
 #define SECCOMP_MODE_FILTER 2
 #endif
 
+#ifndef SECCOMP_RET_ALLOW
+struct seccomp_data {
+	int nr;
+	__u32 arch;
+	__u64 instruction_pointer;
+	__u64 args[6];
+};
+#endif
+
+#ifndef SECCOMP_RET_KILL_PROCESS
+#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */
+#define SECCOMP_RET_KILL_THREAD	 0x00000000U /* kill the thread */
+#endif
 #ifndef SECCOMP_RET_KILL
-#define SECCOMP_RET_KILL        0x00000000U /* kill the task immediately */
+#define SECCOMP_RET_KILL	 SECCOMP_RET_KILL_THREAD
 #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 */
+#endif
+#ifndef SECCOMP_RET_LOG
+#define SECCOMP_RET_LOG		 0x7ffc0000U /* allow after logging */
+#endif
 
-/* Masks for the return value sections. */
-#define SECCOMP_RET_ACTION      0x7fff0000U
-#define SECCOMP_RET_DATA        0x0000ffffU
+#ifndef __NR_seccomp
+# if defined(__i386__)
+#  define __NR_seccomp 354
+# elif defined(__x86_64__)
+#  define __NR_seccomp 317
+# elif defined(__arm__)
+#  define __NR_seccomp 383
+# elif defined(__aarch64__)
+#  define __NR_seccomp 277
+# elif defined(__hppa__)
+#  define __NR_seccomp 338
+# elif defined(__powerpc__)
+#  define __NR_seccomp 358
+# elif defined(__s390__)
+#  define __NR_seccomp 348
+# else
+#  warning "seccomp syscall number unknown for this architecture"
+#  define __NR_seccomp 0xffff
+# endif
+#endif
 
-struct seccomp_data {
-	int nr;
-	__u32 arch;
-	__u64 instruction_pointer;
-	__u64 args[6];
-};
+#ifndef SECCOMP_SET_MODE_STRICT
+#define SECCOMP_SET_MODE_STRICT 0
+#endif
+
+#ifndef SECCOMP_SET_MODE_FILTER
+#define SECCOMP_SET_MODE_FILTER 1
+#endif
+
+#ifndef SECCOMP_GET_ACTION_AVAIL
+#define SECCOMP_GET_ACTION_AVAIL 2
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_TSYNC
+#define SECCOMP_FILTER_FLAG_TSYNC 1
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_LOG
+#define SECCOMP_FILTER_FLAG_LOG 2
+#endif
+
+#ifndef seccomp
+int seccomp(unsigned int op, unsigned int flags, void *args)
+{
+	errno = 0;
+	return syscall(__NR_seccomp, op, flags, args);
+}
 #endif
 
 #if __BYTE_ORDER == __LITTLE_ENDIAN
@@ -136,7 +190,7 @@ TEST(no_new_privs_support)
 	}
 }
 
-/* Tests kernel support by checking for a copy_from_user() fault on * NULL. */
+/* Tests kernel support by checking for a copy_from_user() fault on NULL. */
 TEST(mode_filter_support)
 {
 	long ret;
@@ -342,6 +396,28 @@ TEST(empty_prog)
 	EXPECT_EQ(EINVAL, errno);
 }
 
+TEST(log_all)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG),
+	};
+	struct sock_fprog prog = {
+		.len = (unsigned short)ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+	long ret;
+	pid_t parent = getppid();
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+	ASSERT_EQ(0, ret);
+
+	/* getppid() should succeed and be logged (no check for logging) */
+	EXPECT_EQ(parent, syscall(__NR_getppid));
+}
+
 TEST_SIGNAL(unknown_ret_is_kill_inside, SIGSYS)
 {
 	struct sock_filter filter[] = {
@@ -520,6 +596,117 @@ TEST_SIGNAL(KILL_one_arg_six, SIGSYS)
 	close(fd);
 }
 
+/* This is a thread task to die via seccomp filter violation. */
+void *kill_thread(void *data)
+{
+	bool die = (bool)data;
+
+	if (die) {
+		prctl(PR_GET_SECCOMP, 0, 0, 0, 0);
+		return (void *)SIBLING_EXIT_FAILURE;
+	}
+
+	return (void *)SIBLING_EXIT_UNKILLED;
+}
+
+/* Prepare a thread that will kill itself or both of us. */
+void kill_thread_or_group(struct __test_metadata *_metadata, bool kill_process)
+{
+	pthread_t thread;
+	void *status;
+	/* Kill only when calling __NR_prctl. */
+	struct sock_filter filter_thread[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_THREAD),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog_thread = {
+		.len = (unsigned short)ARRAY_SIZE(filter_thread),
+		.filter = filter_thread,
+	};
+	struct sock_filter filter_process[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_PROCESS),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog_process = {
+		.len = (unsigned short)ARRAY_SIZE(filter_process),
+		.filter = filter_process,
+	};
+
+	ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0,
+			     kill_process ? &prog_process : &prog_thread));
+
+	/*
+	 * Add the KILL_THREAD rule again to make sure that the KILL_PROCESS
+	 * flag cannot be downgraded by a new filter.
+	 */
+	ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog_thread));
+
+	/* Start a thread that will exit immediately. */
+	ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)false));
+	ASSERT_EQ(0, pthread_join(thread, &status));
+	ASSERT_EQ(SIBLING_EXIT_UNKILLED, (unsigned long)status);
+
+	/* Start a thread that will die immediately. */
+	ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)true));
+	ASSERT_EQ(0, pthread_join(thread, &status));
+	ASSERT_NE(SIBLING_EXIT_FAILURE, (unsigned long)status);
+
+	/*
+	 * If we get here, only the spawned thread died. Let the parent know
+	 * the whole process didn't die (i.e. this thread, the spawner,
+	 * stayed running).
+	 */
+	exit(42);
+}
+
+TEST(KILL_thread)
+{
+	int status;
+	pid_t child_pid;
+
+	child_pid = fork();
+	ASSERT_LE(0, child_pid);
+	if (child_pid == 0) {
+		kill_thread_or_group(_metadata, false);
+		_exit(38);
+	}
+
+	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
+
+	/* If only the thread was killed, we'll see exit 42. */
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(42, WEXITSTATUS(status));
+}
+
+TEST(KILL_process)
+{
+	int status;
+	pid_t child_pid;
+
+	child_pid = fork();
+	ASSERT_LE(0, child_pid);
+	if (child_pid == 0) {
+		kill_thread_or_group(_metadata, true);
+		_exit(38);
+	}
+
+	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
+
+	/* If the entire process was killed, we'll see SIGSYS. */
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_EQ(SIGSYS, WTERMSIG(status));
+}
+
 /* TODO(wad) add 64-bit versus 32-bit arg tests. */
 TEST(arg_out_of_range)
 {
@@ -541,26 +728,30 @@ TEST(arg_out_of_range)
 	EXPECT_EQ(EINVAL, errno);
 }
 
+#define ERRNO_FILTER(name, errno)					\
+	struct sock_filter _read_filter_##name[] = {			\
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,				\
+			offsetof(struct seccomp_data, nr)),		\
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),	\
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | errno),	\
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),		\
+	};								\
+	struct sock_fprog prog_##name = {				\
+		.len = (unsigned short)ARRAY_SIZE(_read_filter_##name),	\
+		.filter = _read_filter_##name,				\
+	}
+
+/* Make sure basic errno values are correctly passed through a filter. */
 TEST(ERRNO_valid)
 {
-	struct sock_filter filter[] = {
-		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
-			offsetof(struct seccomp_data, nr)),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | E2BIG),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
-	};
-	struct sock_fprog prog = {
-		.len = (unsigned short)ARRAY_SIZE(filter),
-		.filter = filter,
-	};
+	ERRNO_FILTER(valid, E2BIG);
 	long ret;
 	pid_t parent = getppid();
 
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	ASSERT_EQ(0, ret);
 
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_valid);
 	ASSERT_EQ(0, ret);
 
 	EXPECT_EQ(parent, syscall(__NR_getppid));
@@ -568,26 +759,17 @@ TEST(ERRNO_valid)
 	EXPECT_EQ(E2BIG, errno);
 }
 
+/* Make sure an errno of zero is correctly handled by the arch code. */
 TEST(ERRNO_zero)
 {
-	struct sock_filter filter[] = {
-		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
-			offsetof(struct seccomp_data, nr)),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | 0),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
-	};
-	struct sock_fprog prog = {
-		.len = (unsigned short)ARRAY_SIZE(filter),
-		.filter = filter,
-	};
+	ERRNO_FILTER(zero, 0);
 	long ret;
 	pid_t parent = getppid();
 
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	ASSERT_EQ(0, ret);
 
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_zero);
 	ASSERT_EQ(0, ret);
 
 	EXPECT_EQ(parent, syscall(__NR_getppid));
@@ -595,26 +777,21 @@ TEST(ERRNO_zero)
 	EXPECT_EQ(0, read(0, NULL, 0));
 }
 
+/*
+ * The SECCOMP_RET_DATA mask is 16 bits wide, but errno is smaller.
+ * This tests that the errno value gets capped correctly, fixed by
+ * 580c57f10768 ("seccomp: cap SECCOMP_RET_ERRNO data to MAX_ERRNO").
+ */
 TEST(ERRNO_capped)
 {
-	struct sock_filter filter[] = {
-		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
-			offsetof(struct seccomp_data, nr)),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | 4096),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
-	};
-	struct sock_fprog prog = {
-		.len = (unsigned short)ARRAY_SIZE(filter),
-		.filter = filter,
-	};
+	ERRNO_FILTER(capped, 4096);
 	long ret;
 	pid_t parent = getppid();
 
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	ASSERT_EQ(0, ret);
 
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_capped);
 	ASSERT_EQ(0, ret);
 
 	EXPECT_EQ(parent, syscall(__NR_getppid));
@@ -622,6 +799,37 @@ TEST(ERRNO_capped)
 	EXPECT_EQ(4095, errno);
 }
 
+/*
+ * Filters are processed in reverse order: last applied is executed first.
+ * Since only the SECCOMP_RET_ACTION mask is tested for return values, the
+ * SECCOMP_RET_DATA mask results will follow the most recently applied
+ * matching filter return (and not the lowest or highest value).
+ */
+TEST(ERRNO_order)
+{
+	ERRNO_FILTER(first,  11);
+	ERRNO_FILTER(second, 13);
+	ERRNO_FILTER(third,  12);
+	long ret;
+	pid_t parent = getppid();
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_first);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_second);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_third);
+	ASSERT_EQ(0, ret);
+
+	EXPECT_EQ(parent, syscall(__NR_getppid));
+	EXPECT_EQ(-1, read(0, NULL, 0));
+	EXPECT_EQ(12, errno);
+}
+
 FIXTURE_DATA(TRAP) {
 	struct sock_fprog prog;
 };
@@ -735,6 +943,7 @@ TEST_F(TRAP, handler)
 
 FIXTURE_DATA(precedence) {
 	struct sock_fprog allow;
+	struct sock_fprog log;
 	struct sock_fprog trace;
 	struct sock_fprog error;
 	struct sock_fprog trap;
@@ -746,6 +955,13 @@ FIXTURE_SETUP(precedence)
 	struct sock_filter allow_insns[] = {
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
 	};
+	struct sock_filter log_insns[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG),
+	};
 	struct sock_filter trace_insns[] = {
 		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
 			offsetof(struct seccomp_data, nr)),
@@ -782,6 +998,7 @@ FIXTURE_SETUP(precedence)
 	memcpy(self->_x.filter, &_x##_insns, sizeof(_x##_insns)); \
 	self->_x.len = (unsigned short)ARRAY_SIZE(_x##_insns)
 	FILTER_ALLOC(allow);
+	FILTER_ALLOC(log);
 	FILTER_ALLOC(trace);
 	FILTER_ALLOC(error);
 	FILTER_ALLOC(trap);
@@ -792,6 +1009,7 @@ FIXTURE_TEARDOWN(precedence)
 {
 #define FILTER_FREE(_x) if (self->_x.filter) free(self->_x.filter)
 	FILTER_FREE(allow);
+	FILTER_FREE(log);
 	FILTER_FREE(trace);
 	FILTER_FREE(error);
 	FILTER_FREE(trap);
@@ -809,6 +1027,8 @@ TEST_F(precedence, allow_ok)
 
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -833,6 +1053,8 @@ TEST_F_SIGNAL(precedence, kill_is_highest, SIGSYS)
 
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -864,6 +1086,8 @@ TEST_F_SIGNAL(precedence, kill_is_highest_in_any_order, SIGSYS)
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
@@ -885,6 +1109,8 @@ TEST_F_SIGNAL(precedence, trap_is_second, SIGSYS)
 
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -910,6 +1136,8 @@ TEST_F_SIGNAL(precedence, trap_is_second_in_any_order, SIGSYS)
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -931,6 +1159,8 @@ TEST_F(precedence, errno_is_third)
 
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
@@ -949,6 +1179,8 @@ TEST_F(precedence, errno_is_third_in_any_order)
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	ASSERT_EQ(0, ret);
 
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
@@ -971,6 +1203,8 @@ TEST_F(precedence, trace_is_fourth)
 
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
 	ASSERT_EQ(0, ret);
 	/* Should work just fine. */
@@ -992,12 +1226,54 @@ TEST_F(precedence, trace_is_fourth_in_any_order)
 	ASSERT_EQ(0, ret);
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
 	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
 	/* Should work just fine. */
 	EXPECT_EQ(parent, syscall(__NR_getppid));
 	/* No ptracer */
 	EXPECT_EQ(-1, syscall(__NR_getpid));
 }
 
+TEST_F(precedence, log_is_fifth)
+{
+	pid_t mypid, parent;
+	long ret;
+
+	mypid = getpid();
+	parent = getppid();
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
+	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
+	/* Should work just fine. */
+	EXPECT_EQ(parent, syscall(__NR_getppid));
+	/* Should also work just fine */
+	EXPECT_EQ(mypid, syscall(__NR_getpid));
+}
+
+TEST_F(precedence, log_is_fifth_in_any_order)
+{
+	pid_t mypid, parent;
+	long ret;
+
+	mypid = getpid();
+	parent = getppid();
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+	ASSERT_EQ(0, ret);
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
+	ASSERT_EQ(0, ret);
+	/* Should work just fine. */
+	EXPECT_EQ(parent, syscall(__NR_getppid));
+	/* Should also work just fine */
+	EXPECT_EQ(mypid, syscall(__NR_getpid));
+}
+
 #ifndef PTRACE_O_TRACESECCOMP
 #define PTRACE_O_TRACESECCOMP	0x00000080
 #endif
@@ -1262,6 +1538,13 @@ TEST_F(TRACE_poke, getpid_runs_normally)
 # error "Do not know how to find your architecture's registers and syscalls"
 #endif
 
+/* When the syscall return can't be changed, stub out the tests for it. */
+#ifdef SYSCALL_NUM_RET_SHARE_REG
+# define EXPECT_SYSCALL_RETURN(val, action)	EXPECT_EQ(-1, action)
+#else
+# define EXPECT_SYSCALL_RETURN(val, action)	EXPECT_EQ(val, action)
+#endif
+
 /* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for
  * architectures without HAVE_ARCH_TRACEHOOK (e.g. User-mode Linux).
  */
@@ -1357,7 +1640,7 @@ void change_syscall(struct __test_metadata *_metadata,
 #ifdef SYSCALL_NUM_RET_SHARE_REG
 		TH_LOG("Can't modify syscall return on this architecture");
 #else
-		regs.SYSCALL_RET = 1;
+		regs.SYSCALL_RET = EPERM;
 #endif
 
 #ifdef HAVE_GETREGS
@@ -1426,6 +1709,8 @@ void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee,
 
 	if (nr == __NR_getpid)
 		change_syscall(_metadata, tracee, __NR_getppid);
+	if (nr == __NR_open)
+		change_syscall(_metadata, tracee, -1);
 }
 
 FIXTURE_DATA(TRACE_syscall) {
@@ -1480,6 +1765,28 @@ FIXTURE_TEARDOWN(TRACE_syscall)
 		free(self->prog.filter);
 }
 
+TEST_F(TRACE_syscall, ptrace_syscall_redirected)
+{
+	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
+	teardown_trace_fixture(_metadata, self->tracer);
+	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
+					   true);
+
+	/* Tracer will redirect getpid to getppid. */
+	EXPECT_NE(self->mypid, syscall(__NR_getpid));
+}
+
+TEST_F(TRACE_syscall, ptrace_syscall_dropped)
+{
+	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
+	teardown_trace_fixture(_metadata, self->tracer);
+	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
+					   true);
+
+	/* Tracer should skip the open syscall, resulting in EPERM. */
+	EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_open));
+}
+
 TEST_F(TRACE_syscall, syscall_allowed)
 {
 	long ret;
@@ -1520,13 +1827,8 @@ TEST_F(TRACE_syscall, syscall_dropped)
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
 	ASSERT_EQ(0, ret);
 
-#ifdef SYSCALL_NUM_RET_SHARE_REG
-	/* gettid has been skipped */
-	EXPECT_EQ(-1, syscall(__NR_gettid));
-#else
 	/* gettid has been skipped and an altered return value stored. */
-	EXPECT_EQ(1, syscall(__NR_gettid));
-#endif
+	EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_gettid));
 	EXPECT_NE(self->mytid, syscall(__NR_gettid));
 }
 
@@ -1557,6 +1859,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE)
 	ASSERT_EQ(0, ret);
 
 	/* Tracer will redirect getpid to getppid, and we should see EPERM. */
+	errno = 0;
 	EXPECT_EQ(-1, syscall(__NR_getpid));
 	EXPECT_EQ(EPERM, errno);
 }
@@ -1654,47 +1957,6 @@ TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS)
 	EXPECT_NE(self->mypid, syscall(__NR_getpid));
 }
 
-#ifndef __NR_seccomp
-# if defined(__i386__)
-#  define __NR_seccomp 354
-# elif defined(__x86_64__)
-#  define __NR_seccomp 317
-# elif defined(__arm__)
-#  define __NR_seccomp 383
-# elif defined(__aarch64__)
-#  define __NR_seccomp 277
-# elif defined(__hppa__)
-#  define __NR_seccomp 338
-# elif defined(__powerpc__)
-#  define __NR_seccomp 358
-# elif defined(__s390__)
-#  define __NR_seccomp 348
-# else
-#  warning "seccomp syscall number unknown for this architecture"
-#  define __NR_seccomp 0xffff
-# endif
-#endif
-
-#ifndef SECCOMP_SET_MODE_STRICT
-#define SECCOMP_SET_MODE_STRICT 0
-#endif
-
-#ifndef SECCOMP_SET_MODE_FILTER
-#define SECCOMP_SET_MODE_FILTER 1
-#endif
-
-#ifndef SECCOMP_FILTER_FLAG_TSYNC
-#define SECCOMP_FILTER_FLAG_TSYNC 1
-#endif
-
-#ifndef seccomp
-int seccomp(unsigned int op, unsigned int flags, void *args)
-{
-	errno = 0;
-	return syscall(__NR_seccomp, op, flags, args);
-}
-#endif
-
 TEST(seccomp_syscall)
 {
 	struct sock_filter filter[] = {
@@ -1783,6 +2045,67 @@ TEST(seccomp_syscall_mode_lock)
 	}
 }
 
+/*
+ * Test detection of known and unknown filter flags. Userspace needs to be able
+ * to check if a filter flag is supported by the current kernel and a good way
+ * of doing that is by attempting to enter filter mode, with the flag bit in
+ * question set, and a NULL pointer for the _args_ parameter. EFAULT indicates
+ * that the flag is valid and EINVAL indicates that the flag is invalid.
+ */
+TEST(detect_seccomp_filter_flags)
+{
+	unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC,
+				 SECCOMP_FILTER_FLAG_LOG };
+	unsigned int flag, all_flags;
+	int i;
+	long ret;
+
+	/* Test detection of known-good filter flags */
+	for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
+		flag = flags[i];
+		ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+		ASSERT_NE(ENOSYS, errno) {
+			TH_LOG("Kernel does not support seccomp syscall!");
+		}
+		EXPECT_EQ(-1, ret);
+		EXPECT_EQ(EFAULT, errno) {
+			TH_LOG("Failed to detect that a known-good filter flag (0x%X) is supported!",
+			       flag);
+		}
+
+		all_flags |= flag;
+	}
+
+	/* Test detection of all known-good filter flags */
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EFAULT, errno) {
+		TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!",
+		       all_flags);
+	}
+
+	/* Test detection of an unknown filter flag */
+	flag = -1;
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno) {
+		TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported!",
+		       flag);
+	}
+
+	/*
+	 * Test detection of an unknown filter flag that may simply need to be
+	 * added to this test
+	 */
+	flag = flags[ARRAY_SIZE(flags) - 1] << 1;
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno) {
+		TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported! Does a new flag need to be added to this test?",
+		       flag);
+	}
+}
+
 TEST(TSYNC_first)
 {
 	struct sock_filter filter[] = {
@@ -2421,6 +2744,99 @@ TEST(syscall_restart)
 		_metadata->passed = 0;
 }
 
+TEST_SIGNAL(filter_flag_log, SIGSYS)
+{
+	struct sock_filter allow_filter[] = {
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_filter kill_filter[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 0, 1),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog allow_prog = {
+		.len = (unsigned short)ARRAY_SIZE(allow_filter),
+		.filter = allow_filter,
+	};
+	struct sock_fprog kill_prog = {
+		.len = (unsigned short)ARRAY_SIZE(kill_filter),
+		.filter = kill_filter,
+	};
+	long ret;
+	pid_t parent = getppid();
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	/* Verify that the FILTER_FLAG_LOG flag isn't accepted in strict mode */
+	ret = seccomp(SECCOMP_SET_MODE_STRICT, SECCOMP_FILTER_FLAG_LOG,
+		      &allow_prog);
+	ASSERT_NE(ENOSYS, errno) {
+		TH_LOG("Kernel does not support seccomp syscall!");
+	}
+	EXPECT_NE(0, ret) {
+		TH_LOG("Kernel accepted FILTER_FLAG_LOG flag in strict mode!");
+	}
+	EXPECT_EQ(EINVAL, errno) {
+		TH_LOG("Kernel returned unexpected errno for FILTER_FLAG_LOG flag in strict mode!");
+	}
+
+	/* Verify that a simple, permissive filter can be added with no flags */
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &allow_prog);
+	EXPECT_EQ(0, ret);
+
+	/* See if the same filter can be added with the FILTER_FLAG_LOG flag */
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG,
+		      &allow_prog);
+	ASSERT_NE(EINVAL, errno) {
+		TH_LOG("Kernel does not support the FILTER_FLAG_LOG flag!");
+	}
+	EXPECT_EQ(0, ret);
+
+	/* Ensure that the kill filter works with the FILTER_FLAG_LOG flag */
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG,
+		      &kill_prog);
+	EXPECT_EQ(0, ret);
+
+	EXPECT_EQ(parent, syscall(__NR_getppid));
+	/* getpid() should never return. */
+	EXPECT_EQ(0, syscall(__NR_getpid));
+}
+
+TEST(get_action_avail)
+{
+	__u32 actions[] = { SECCOMP_RET_KILL_THREAD, SECCOMP_RET_TRAP,
+			    SECCOMP_RET_ERRNO, SECCOMP_RET_TRACE,
+			    SECCOMP_RET_LOG,   SECCOMP_RET_ALLOW };
+	__u32 unknown_action = 0x10000000U;
+	int i;
+	long ret;
+
+	ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[0]);
+	ASSERT_NE(ENOSYS, errno) {
+		TH_LOG("Kernel does not support seccomp syscall!");
+	}
+	ASSERT_NE(EINVAL, errno) {
+		TH_LOG("Kernel does not support SECCOMP_GET_ACTION_AVAIL operation!");
+	}
+	EXPECT_EQ(ret, 0);
+
+	for (i = 0; i < ARRAY_SIZE(actions); i++) {
+		ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[i]);
+		EXPECT_EQ(ret, 0) {
+			TH_LOG("Expected action (0x%X) not available!",
+			       actions[i]);
+		}
+	}
+
+	/* Check that an unknown action is handled properly (EOPNOTSUPP) */
+	ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &unknown_action);
+	EXPECT_EQ(ret, -1);
+	EXPECT_EQ(errno, EOPNOTSUPP);
+}
+
 /*
  * TODO:
  * - add microbenchmarks
@@ -2429,6 +2845,8 @@ TEST(syscall_restart)
  * - endianness checking when appropriate
  * - 64-bit arg prodding
  * - arch value testing (x86 modes especially)
+ * - verify that FILTER_FLAG_LOG filters generate log messages
+ * - verify that RET_LOG generates log messages
  * - ...
  */