main: add configuration option to alter capability bounding set for PID 1

This also ensures that caps dropped from the bounding set are also
dropped from the inheritable set, to be extra-secure. Usually that should
change very little though as the inheritable set is empty for all our uses
anyway.

9 files changed, 158 insertions, 115 deletions

diff --git a/src/core/execute.c b/src/core/execute.c
index bb841b7fcf..9c2006ebc7 100644
--- a/src/core/execute.c
+++ b/src/core/execute.c
@@ -870,68 +870,6 @@ fail:
 }
 #endif
 
-static int do_capability_bounding_set_drop(uint64_t drop) {
-        unsigned long i;
-        cap_t old_cap = NULL, new_cap = NULL;
-        cap_flag_value_t fv;
-        int r;
-
-        /* If we are run as PID 1 we will lack CAP_SETPCAP by default
-         * in the effective set (yes, the kernel drops that when
-         * executing init!), so get it back temporarily so that we can
-         * call PR_CAPBSET_DROP. */
-
-        old_cap = cap_get_proc();
-        if (!old_cap)
-                return -errno;
-
-        if (cap_get_flag(old_cap, CAP_SETPCAP, CAP_EFFECTIVE, &fv) < 0) {
-                r = -errno;
-                goto finish;
-        }
-
-        if (fv != CAP_SET) {
-                static const cap_value_t v = CAP_SETPCAP;
-
-                new_cap = cap_dup(old_cap);
-                if (!new_cap) {
-                        r = -errno;
-                        goto finish;
-                }
-
-                if (cap_set_flag(new_cap, CAP_EFFECTIVE, 1, &v, CAP_SET) < 0) {
-                        r = -errno;
-                        goto finish;
-                }
-
-                if (cap_set_proc(new_cap) < 0) {
-                        r = -errno;
-                        goto finish;
-                }
-        }
-
-        for (i = 0; i <= cap_last_cap(); i++)
-                if (drop & ((uint64_t) 1ULL << (uint64_t) i)) {
-                        if (prctl(PR_CAPBSET_DROP, i) < 0) {
-                                r = -errno;
-                                goto finish;
-                        }
-                }
-
-        r = 0;
-
-finish:
-        if (new_cap)
-                cap_free(new_cap);
-
-        if (old_cap) {
-                cap_set_proc(old_cap);
-                cap_free(old_cap);
-        }
-
-        return r;
-}
-
 static void rename_process_from_path(const char *path) {
         char process_name[11];
         const char *p;
@@ -1398,7 +1336,7 @@ int exec_spawn(ExecCommand *command,
                         }
 
                         if (context->capability_bounding_set_drop) {
-                                err = do_capability_bounding_set_drop(context->capability_bounding_set_drop);
+                                err = capability_bounding_set_drop(context->capability_bounding_set_drop, false);
                                 if (err < 0) {
                                         r = EXIT_CAPABILITIES;
                                         goto fail_child;
diff --git a/src/core/load-fragment-gperf.gperf.m4 b/src/core/load-fragment-gperf.gperf.m4
index ea502bd288..6f2a0d63ef 100644
--- a/src/core/load-fragment-gperf.gperf.m4
+++ b/src/core/load-fragment-gperf.gperf.m4
@@ -46,7 +46,7 @@ $1.SyslogLevel,                  config_parse_level,                 0,
 $1.SyslogLevelPrefix,            config_parse_bool,                  0,                             offsetof($1, exec_context.syslog_level_prefix)
 $1.Capabilities,                 config_parse_exec_capabilities,     0,                             offsetof($1, exec_context)
 $1.SecureBits,                   config_parse_exec_secure_bits,      0,                             offsetof($1, exec_context)
-$1.CapabilityBoundingSet,        config_parse_exec_bounding_set,     0,                             offsetof($1, exec_context)
+$1.CapabilityBoundingSet,        config_parse_bounding_set,          0,                             offsetof($1, exec_context.capability_bounding_set_drop)
 $1.TimerSlackNSec,               config_parse_exec_timer_slack_nsec, 0,                             offsetof($1, exec_context)
 $1.LimitCPU,                     config_parse_limit,                 RLIMIT_CPU,                    offsetof($1, exec_context.rlimit)
 $1.LimitFSIZE,                   config_parse_limit,                 RLIMIT_FSIZE,                  offsetof($1, exec_context.rlimit)
diff --git a/src/core/load-fragment.c b/src/core/load-fragment.c
index d2267722dd..ff6e13e599 100644
--- a/src/core/load-fragment.c
+++ b/src/core/load-fragment.c
@@ -931,7 +931,7 @@ int config_parse_exec_secure_bits(
         return 0;
 }
 
-int config_parse_exec_bounding_set(
+int config_parse_bounding_set(
                 const char *filename,
                 unsigned line,
                 const char *section,
@@ -941,7 +941,7 @@ int config_parse_exec_bounding_set(
                 void *data,
                 void *userdata) {
 
-        ExecContext *c = data;
+        uint64_t *capability_bounding_set_drop = data;
         char *w;
         size_t l;
         char *state;
@@ -968,7 +968,8 @@ int config_parse_exec_bounding_set(
                 int r;
                 cap_value_t cap;
 
-                if (!(t = strndup(w, l)))
+                t = strndup(w, l);
+                if (!t)
                         return -ENOMEM;
 
                 r = cap_from_name(t, &cap);
@@ -983,9 +984,9 @@ int config_parse_exec_bounding_set(
         }
 
         if (invert)
-                c->capability_bounding_set_drop |= sum;
+                *capability_bounding_set_drop |= sum;
         else
-                c->capability_bounding_set_drop |= ~sum;
+                *capability_bounding_set_drop |= ~sum;
 
         return 0;
 }
@@ -2447,7 +2448,7 @@ void unit_dump_config_items(FILE *f) {
                 { config_parse_level,                 "LEVEL" },
                 { config_parse_exec_capabilities,     "CAPABILITIES" },
                 { config_parse_exec_secure_bits,      "SECUREBITS" },
-                { config_parse_exec_bounding_set,     "BOUNDINGSET" },
+                { config_parse_bounding_set,          "BOUNDINGSET" },
                 { config_parse_exec_timer_slack_nsec, "TIMERSLACK" },
                 { config_parse_limit,                 "LIMIT" },
                 { config_parse_unit_cgroup,           "CGROUP [...]" },
diff --git a/src/core/load-fragment.h b/src/core/load-fragment.h
index 3b2ed096b5..6b382494aa 100644
--- a/src/core/load-fragment.h
+++ b/src/core/load-fragment.h
@@ -56,7 +56,7 @@ int config_parse_exec_cpu_sched_prio(const char *filename, unsigned line, const
 int config_parse_exec_cpu_affinity(const char *filename, unsigned line, const char *section, const char *lvalue, int ltype, const char *rvalue, void *data, void *userdata);
 int config_parse_exec_capabilities(const char *filename, unsigned line, const char *section, const char *lvalue, int ltype, const char *rvalue, void *data, void *userdata);
 int config_parse_exec_secure_bits(const char *filename, unsigned line, const char *section, const char *lvalue, int ltype, const char *rvalue, void *data, void *userdata);
-int config_parse_exec_bounding_set(const char *filename, unsigned line, const char *section, const char *lvalue, int ltype, const char *rvalue, void *data, void *userdata);
+int config_parse_bounding_set(const char *filename, unsigned line, const char *section, const char *lvalue, int ltype, const char *rvalue, void *data, void *userdata);
 int config_parse_exec_timer_slack_nsec(const char *filename, unsigned line, const char *section, const char *lvalue, int ltype, const char *rvalue, void *data, void *userdata);
 int config_parse_limit(const char *filename, unsigned line, const char *section, const char *lvalue, int ltype, const char *rvalue, void *data, void *userdata);
 int config_parse_unit_cgroup(const char *filename, unsigned line, const char *section, const char *lvalue, int ltype, const char *rvalue, void *data, void *userdata);
diff --git a/src/core/main.c b/src/core/main.c
index 4d9a2d453e..9248c388a4 100644
--- a/src/core/main.c
+++ b/src/core/main.c
@@ -50,6 +50,7 @@
 #include "watchdog.h"
 #include "path-util.h"
 #include "switch-root.h"
+#include "capability.h"
 
 #include "mount-setup.h"
 #include "loopback-setup.h"
@@ -88,6 +89,7 @@ static ExecOutput arg_default_std_error = EXEC_OUTPUT_INHERIT;
 static usec_t arg_runtime_watchdog = 0;
 static usec_t arg_shutdown_watchdog = 10 * USEC_PER_MINUTE;
 static struct rlimit *arg_default_rlimit[RLIMIT_NLIMITS] = {};
+static uint64_t arg_capability_bounding_set_drop = 0;
 
 static FILE* serialization = NULL;
 
@@ -678,6 +680,7 @@ static int parse_config_file(void) {
                 { "Manager", "JoinControllers",       config_parse_join_controllers, 0, &arg_join_controllers },
                 { "Manager", "RuntimeWatchdogSec",    config_parse_usec,         0, &arg_runtime_watchdog    },
                 { "Manager", "ShutdownWatchdogSec",   config_parse_usec,         0, &arg_shutdown_watchdog   },
+                { "Manager", "CapabilityBoundingSet", config_parse_bounding_set, 0, &arg_capability_bounding_set_drop },
                 { "Manager", "DefaultLimitCPU",       config_parse_limit,        0, &arg_default_rlimit[RLIMIT_CPU]},
                 { "Manager", "DefaultLimitFSIZE",     config_parse_limit,        0, &arg_default_rlimit[RLIMIT_FSIZE]},
                 { "Manager", "DefaultLimitDATA",      config_parse_limit,        0, &arg_default_rlimit[RLIMIT_DATA]},
@@ -1484,6 +1487,14 @@ int main(int argc, char *argv[]) {
         if (arg_running_as == MANAGER_SYSTEM && arg_runtime_watchdog > 0)
                 watchdog_set_timeout(&arg_runtime_watchdog);
 
+        if (arg_capability_bounding_set_drop) {
+                r = capability_bounding_set_drop(arg_capability_bounding_set_drop, true);
+                if (r < 0) {
+                        log_error("Failed to drop capability bounding set: %s", strerror(-r));
+                        goto finish;
+                }
+        }
+
         r = manager_new(arg_running_as, &m);
         if (r < 0) {
                 log_error("Failed to allocate manager object: %s", strerror(-r));
diff --git a/src/core/system.conf b/src/core/system.conf
index 2b14d3e31e..7b9171b803 100644
--- a/src/core/system.conf
+++ b/src/core/system.conf
@@ -24,3 +24,20 @@
 #JoinControllers=cpu,cpuacct
 #RuntimeWatchdogSec=0
 #ShutdownWatchdogSec=10min
+#CapabilityBoundingSet=
+#DefaultLimitCPU=
+#DefaultLimitFSIZE=
+#DefaultLimitDATA=
+#DefaultLimitSTACK=
+#DefaultLimitCORE=
+#DefaultLimitRSS=
+#DefaultLimitNOFILE=
+#DefaultLimitAS=
+#DefaultLimitNPROC=
+#DefaultLimitMEMLOCK=
+#DefaultLimitLOCKS=
+#DefaultLimitSIGPENDING=
+#DefaultLimitMSGQUEUE=
+#DefaultLimitNICE=
+#DefaultLimitRTPRIO=
+#DefaultLimitRTTIME=
diff --git a/src/nspawn/nspawn.c b/src/nspawn/nspawn.c
index 31e8b015df..8a5eb34c7f 100644
--- a/src/nspawn/nspawn.c
+++ b/src/nspawn/nspawn.c
@@ -544,49 +544,31 @@ static int setup_hostname(void) {
 }
 
 static int drop_capabilities(void) {
-        static const unsigned long retain[] = {
-                CAP_CHOWN,
-                CAP_DAC_OVERRIDE,
-                CAP_DAC_READ_SEARCH,
-                CAP_FOWNER,
-                CAP_FSETID,
-                CAP_IPC_OWNER,
-                CAP_KILL,
-                CAP_LEASE,
-                CAP_LINUX_IMMUTABLE,
-                CAP_NET_BIND_SERVICE,
-                CAP_NET_BROADCAST,
-                CAP_NET_RAW,
-                CAP_SETGID,
-                CAP_SETFCAP,
-                CAP_SETPCAP,
-                CAP_SETUID,
-                CAP_SYS_ADMIN,
-                CAP_SYS_CHROOT,
-                CAP_SYS_NICE,
-                CAP_SYS_PTRACE,
-                CAP_SYS_TTY_CONFIG
-        };
-
-        unsigned long l;
-
-        for (l = 0; l <= cap_last_cap(); l++) {
-                unsigned i;
-
-                for (i = 0; i < ELEMENTSOF(retain); i++)
-                        if (retain[i] == l)
-                                break;
-
-                if (i < ELEMENTSOF(retain))
-                        continue;
 
-                if (prctl(PR_CAPBSET_DROP, l) < 0) {
-                        log_error("PR_CAPBSET_DROP failed: %m");
-                        return -errno;
-                }
-        }
-
-        return 0;
+        static const uint64_t retain =
+                (1ULL << CAP_CHOWN) |
+                (1ULL << CAP_DAC_OVERRIDE) |
+                (1ULL << CAP_DAC_READ_SEARCH) |
+                (1ULL << CAP_FOWNER) |
+                (1ULL << CAP_FSETID) |
+                (1ULL << CAP_IPC_OWNER) |
+                (1ULL << CAP_KILL) |
+                (1ULL << CAP_LEASE) |
+                (1ULL << CAP_LINUX_IMMUTABLE) |
+                (1ULL << CAP_NET_BIND_SERVICE) |
+                (1ULL << CAP_NET_BROADCAST) |
+                (1ULL << CAP_NET_RAW) |
+                (1ULL << CAP_SETGID) |
+                (1ULL << CAP_SETFCAP) |
+                (1ULL << CAP_SETPCAP) |
+                (1ULL << CAP_SETUID) |
+                (1ULL << CAP_SYS_ADMIN) |
+                (1ULL << CAP_SYS_CHROOT) |
+                (1ULL << CAP_SYS_NICE) |
+                (1ULL << CAP_SYS_PTRACE) |
+                (1ULL << CAP_SYS_TTY_CONFIG);
+
+        return capability_bounding_set_drop(~retain, false);
 }
 
 static int is_os_tree(const char *path) {
@@ -1041,8 +1023,10 @@ int main(int argc, char *argv[]) {
 
                 loopback_setup();
 
-                if (drop_capabilities() < 0)
+                if (drop_capabilities() < 0) {
+                        log_error("drop_capabilities() failed: %m");
                         goto child_fail;
+                }
 
                 if (arg_user) {
 
diff --git a/src/shared/capability.c b/src/shared/capability.c
index b2cd9ed75e..08b7a209da 100644
--- a/src/shared/capability.c
+++ b/src/shared/capability.c
@@ -40,7 +40,8 @@ int have_effective_cap(int value) {
         cap_flag_value_t fv;
         int r;
 
-        if (!(cap = cap_get_proc()))
+        cap = cap_get_proc();
+        if (!cap)
                 return -errno;
 
         if (cap_get_flag(cap, value, CAP_EFFECTIVE, &fv) < 0)
@@ -84,3 +85,89 @@ unsigned long cap_last_cap(void) {
 
         return p;
 }
+
+int capability_bounding_set_drop(uint64_t drop, bool right_now) {
+        unsigned long i;
+        cap_t after_cap = NULL, temp_cap = NULL;
+        cap_flag_value_t fv;
+        int r;
+
+        /* If we are run as PID 1 we will lack CAP_SETPCAP by default
+         * in the effective set (yes, the kernel drops that when
+         * executing init!), so get it back temporarily so that we can
+         * call PR_CAPBSET_DROP. */
+
+        after_cap = cap_get_proc();
+        if (!after_cap)
+                return -errno;
+
+        if (cap_get_flag(after_cap, CAP_SETPCAP, CAP_EFFECTIVE, &fv) < 0) {
+                cap_free(after_cap);
+                return -errno;
+        }
+
+        if (fv != CAP_SET) {
+                static const cap_value_t v = CAP_SETPCAP;
+
+                temp_cap = cap_dup(after_cap);
+                if (!temp_cap) {
+                        r = -errno;
+                        goto finish;
+                }
+
+                if (cap_set_flag(temp_cap, CAP_EFFECTIVE, 1, &v, CAP_SET) < 0) {
+                        r = -errno;
+                        goto finish;
+                }
+
+                if (cap_set_proc(temp_cap) < 0) {
+                        r = -errno;
+                        goto finish;
+                }
+        }
+
+        for (i = 0; i <= cap_last_cap(); i++) {
+
+                if (drop & ((uint64_t) 1ULL << (uint64_t) i)) {
+                        cap_value_t v;
+
+                        /* Drop it from the bounding set */
+                        if (prctl(PR_CAPBSET_DROP, i) < 0) {
+                                r = -errno;
+                                goto finish;
+                        }
+                        v = i;
+
+                        /* Also drop it from the inheritable set, so
+                         * that anything we exec() loses the
+                         * capability for good. */
+                        if (cap_set_flag(after_cap, CAP_INHERITABLE, 1, &v, CAP_CLEAR) < 0) {
+                                r = -errno;
+                                goto finish;
+                        }
+
+                        /* If we shall apply this right now drop it
+                         * also from our own capability sets. */
+                        if (right_now) {
+                                if (cap_set_flag(after_cap, CAP_PERMITTED, 1, &v, CAP_CLEAR) < 0 ||
+                                    cap_set_flag(after_cap, CAP_EFFECTIVE, 1, &v, CAP_CLEAR) < 0) {
+                                        r = -errno;
+                                        goto finish;
+                                }
+                        }
+                }
+        }
+
+        r = 0;
+
+finish:
+        if (temp_cap)
+                cap_free(temp_cap);
+
+        if (after_cap) {
+                cap_set_proc(after_cap);
+                cap_free(after_cap);
+        }
+
+        return r;
+}
diff --git a/src/shared/capability.h b/src/shared/capability.h
index 9f9c49cf5b..0cc5dd08aa 100644
--- a/src/shared/capability.h
+++ b/src/shared/capability.h
@@ -22,6 +22,11 @@
   along with systemd; If not, see <http://www.gnu.org/licenses/>.
 ***/
 
+#include <inttypes.h>
+#include <stdbool.h>
+
 unsigned long cap_last_cap(void);
 int have_effective_cap(int value);
+int capability_bounding_set_drop(uint64_t caps, bool right_now);
+
 #endif