seccomp: add new system call filter, suitable as default whitelist for system services

Currently we employ mostly system call blacklisting for our system
services. Let's add a new system call filter group @system-service that
helps turning this around into a whitelist by default.

The new group is very similar to nspawn's default filter list, but in
some ways more restricted (as sethostname() and suchlike shouldn't be
available to most system services just like that) and in others more
relaxed (for example @keyring is blocked in nspawn since it's not
properly virtualized yet in the kernel, but is fine for regular system
services).

4 files changed, 84 insertions, 1 deletions

diff --git a/man/systemd.exec.xml b/man/systemd.exec.xml
index a17db8d850..3bd790b485 100644
--- a/man/systemd.exec.xml
+++ b/man/systemd.exec.xml
@@ -1491,6 +1491,10 @@ RestrictNamespaces=~cgroup net</programlisting>
                 <entry>Synchronizing files and memory to disk: (<citerefentry project='man-pages'><refentrytitle>fsync</refentrytitle><manvolnum>2</manvolnum></citerefentry>, <citerefentry project='man-pages'><refentrytitle>msync</refentrytitle><manvolnum>2</manvolnum></citerefentry>, and related calls)</entry>
               </row>
               <row>
+                <entry>@system-service</entry>
+                <entry>A reasonable set of system calls used by common system services, excluding any special purpose calls. This is the recommended starting point for whitelisting system calls for system services, as it contains what is typically needed by system services, but excludes overly specific interfaces. For example, the following APIs are excluded: <literal>@clock</literal>, <literal>@mount</literal>, <literal>@swap</literal>, <literal>@reboot</literal>.</entry>
+              </row>
+              <row>
                 <entry>@timer</entry>
                 <entry>System calls for scheduling operations by time (<citerefentry project='man-pages'><refentrytitle>alarm</refentrytitle><manvolnum>2</manvolnum></citerefentry>, <citerefentry project='man-pages'><refentrytitle>timer_create</refentrytitle><manvolnum>2</manvolnum></citerefentry>, …)</entry>
               </row>
@@ -1504,6 +1508,14 @@ RestrictNamespaces=~cgroup net</programlisting>
         <command>systemd-analyze syscall-filter</command> to list the actual list of system calls in each
         filter.</para>
 
+        <para>Generally, whitelisting system calls (rather than blacklisting) is the safer mode of operation. It is
+        recommended to enforce system call whitelists for all long-running system services. Specifically, the
+        following lines are a relatively safe basic choice for the majority of system services:</para>
+
+        <programlisting>[Service]
+SystemCallFilter=@system-service
+SystemCallErrorNumber=EPERM</programlisting>
+
         <para>It is recommended to combine the file system namespacing related options with
         <varname>SystemCallFilter=~@mount</varname>, in order to prohibit the unit's processes to undo the
         mappings. Specifically these are the options <varname>PrivateTmp=</varname>,
diff --git a/src/shared/seccomp-util.c b/src/shared/seccomp-util.c
index 517a1b4509..4a02d8c35f 100644
--- a/src/shared/seccomp-util.c
+++ b/src/shared/seccomp-util.c
@@ -756,6 +756,75 @@ const SyscallFilterSet syscall_filter_sets[_SYSCALL_FILTER_SET_MAX] = {
                 "sync_file_range\0"
                 "syncfs\0"
         },
+        [SYSCALL_FILTER_SET_SYSTEM_SERVICE] = {
+                .name = "@system-service",
+                .help = "General system service operations",
+                .value =
+                "@aio\0"
+                "@basic-io\0"
+                "@chown\0"
+                "@default\0"
+                "@file-system\0"
+                "@io-event\0"
+                "@ipc\0"
+                "@keyring\0"
+                "@memlock\0"
+                "@network-io\0"
+                "@process\0"
+                "@resources\0"
+                "@setuid\0"
+                "@signal\0"
+                "@sync\0"
+                "@timer\0"
+                "brk\0"
+                "capget\0"
+                "capset\0"
+                "copy_file_range\0"
+                "fadvise64\0"
+                "fadvise64_64\0"
+                "flock\0"
+                "get_mempolicy\0"
+                "getcpu\0"
+                "getpriority\0"
+                "getrandom\0"
+                "ioctl\0"
+                "ioprio_get\0"
+                "kcmp\0"
+                "madvise\0"
+                "mincore\0"
+                "mprotect\0"
+                "mremap\0"
+                "name_to_handle_at\0"
+                "oldolduname\0"
+                "olduname\0"
+                "personality\0"
+                "readahead\0"
+                "readdir\0"
+                "remap_file_pages\0"
+                "sched_get_priority_max\0"
+                "sched_get_priority_min\0"
+                "sched_getaffinity\0"
+                "sched_getattr\0"
+                "sched_getparam\0"
+                "sched_getscheduler\0"
+                "sched_rr_get_interval\0"
+                "sched_yield\0"
+                "sendfile\0"
+                "sendfile64\0"
+                "setfsgid\0"
+                "setfsgid32\0"
+                "setfsuid\0"
+                "setfsuid32\0"
+                "setpgid\0"
+                "setsid\0"
+                "splice\0"
+                "sysinfo\0"
+                "tee\0"
+                "umask\0"
+                "uname\0"
+                "userfaultfd\0"
+                "vmsplice\0"
+        },
         [SYSCALL_FILTER_SET_TIMER] = {
                 .name = "@timer",
                 .help = "Schedule operations by time",
diff --git a/src/shared/seccomp-util.h b/src/shared/seccomp-util.h
index 7dfff9df78..eac857afb9 100644
--- a/src/shared/seccomp-util.h
+++ b/src/shared/seccomp-util.h
@@ -47,6 +47,7 @@ enum {
         SYSCALL_FILTER_SET_SIGNAL,
         SYSCALL_FILTER_SET_SWAP,
         SYSCALL_FILTER_SET_SYNC,
+        SYSCALL_FILTER_SET_SYSTEM_SERVICE,
         SYSCALL_FILTER_SET_TIMER,
         _SYSCALL_FILTER_SET_MAX
 };
diff --git a/src/test/test-seccomp.c b/src/test/test-seccomp.c
index 33ec680753..d82cb5c1c5 100644
--- a/src/test/test-seccomp.c
+++ b/src/test/test-seccomp.c
@@ -104,7 +104,8 @@ static void test_filter_sets(void) {
                 if (pid == 0) { /* Child? */
                         int fd;
 
-                        if (i == SYSCALL_FILTER_SET_DEFAULT) /* if we look at the default set, whitelist instead of blacklist */
+                        /* if we look at the default set (or one that includes it), whitelist instead of blacklist */
+                        if (IN_SET(i, SYSCALL_FILTER_SET_DEFAULT, SYSCALL_FILTER_SET_SYSTEM_SERVICE))
                                 r = seccomp_load_syscall_filter_set(SCMP_ACT_ERRNO(EUCLEAN), syscall_filter_sets + i, SCMP_ACT_ALLOW);
                         else
                                 r = seccomp_load_syscall_filter_set(SCMP_ACT_ALLOW, syscall_filter_sets + i, SCMP_ACT_ERRNO(EUCLEAN));