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
 

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;
+}