Merge pull request #458 from aanderse/master

Add support for Linux capabilities

.github/workflows/build.yml

@@ -34,7 +34,7 @@ jobs:
       - name: Install dependencies
         run: |
           sudo apt-get -y update
-          sudo apt-get -y install pkg-config tree jq libuev-dev libite-dev
+          sudo apt-get -y install pkg-config tree jq libuev-dev libite-dev libcap-dev
       - uses: actions/checkout@v4
       - name: Static Finit
         run: |

configure.ac

@@ -72,6 +72,10 @@ AC_ARG_ENABLE(cgroup,
         AS_HELP_STRING([--disable-cgroup], [Disable cgroup v2 support, default: autodetect from /sys/fs/cgroup]),,[
         enable_cgroup=yes])
 
+AC_ARG_ENABLE(libcap,
+        AS_HELP_STRING([--disable-libcap], [Disable Linux capabilities support]),,[
+				enable_libcap=yes])
+
 AC_ARG_ENABLE(redirect,
         AS_HELP_STRING([--disable-redirect], [Disable redirection of service output to /dev/null]),,[
 	enable_redirect=yes])
@@ -204,6 +208,16 @@ AS_IF([test "x$enable_kernel_logging" = "xyes"], [
 AS_IF([test "x$enable_cgroup" = "xyes"], [
         AC_DEFINE(CGROUP2_ENABLED, 1, [Autodetect cgroup v2 support from /sys/fs/cgroup])])
 
+AS_IF([test "x$enable_libcap" = "xyes"], [
+	AC_CHECK_LIB([cap], [cap_from_text], [
+		AC_DEFINE(HAVE_LIBCAP, 1, [Have libcap for Linux capabilities support])
+		LIBS="$LIBS -lcap"
+	], [
+		AC_MSG_WARN([libcap not found, capabilities support disabled])
+		enable_libcap=no
+	])
+])
+
 AS_IF([test "x$enable_fastboot" = "xyes"], [
 	AC_DEFINE(FAST_BOOT, 1, [Skip fsck check on filesystems listed in /etc/fstab])])
 
@@ -419,6 +433,7 @@ Optional features:
   Built-in logrotate....: $enable_logrotate
   Replacement libsystemd: $with_libsystemd
   Use cgroup v2.........: $enable_cgroup
+  Use libcap............: $enable_libcap
   Parse kernel cmdline..: $enable_kernel_cmdline
   Keep kernel logging...: $enable_kernel_logging
   Skip fsck check.......: $enable_fastboot

doc/config/capabilities.md

@@ -0,0 +1,176 @@
+Linux Capabilities
+==================
+
+Finit supports Linux capabilities, allowing services to run with minimal
+required privileges instead of running as root. This significantly improves
+system security by following the principle of least privilege.
+
+## Overview
+
+Linux capabilities divide the traditional root privileges into distinct units
+that can be independently granted to processes. For example, a web server only
+needs the capability to bind to privileged ports (< 1024), not full root access.
+
+Finit uses the modern IAB (Inheritable, Ambient, Bounding) API from libcap,
+which is the same approach used by other modern service managers like dinit.
+
+## Basic Usage
+
+Capabilities are specified using the `caps:` directive in service configuration:
+
+```conf
+service [2345] name:nginx \
+        @www-data:www-data \
+        caps:^cap_net_bind_service \
+        /usr/sbin/nginx -g 'daemon off;' \
+        -- Web server
+```
+
+This example allows nginx to bind to privileged ports (like 80 and 443) while
+running as the unprivileged `www-data` user.
+
+## IAB Format
+
+The capability string uses the IAB (Inheritable, Ambient, Bounding) format
+with the following prefixes:
+
+- `^` **Ambient** (and Inheritable) - **Recommended for most use cases**
+  - Capabilities survive across `exec()` calls
+  - Automatically raised to effective after exec
+  - Example: `^cap_net_bind_service`
+
+- `%` **Inheritable** only
+  - Requires the executed binary to have matching file capabilities
+  - Less common, more complex setup
+  - Example: `%cap_net_admin`
+
+- `!` **Bounding** - Block capability from bounding set
+  - Prevents the service from ever acquiring this capability
+  - Useful for security hardening
+  - Example: `!cap_sys_admin`
+
+Multiple capabilities can be specified as a comma-separated list:
+
+```conf
+caps:^cap_net_raw,^cap_net_admin,^cap_net_bind_service
+```
+
+## Common Use Cases
+
+### Web Server (Privileged Ports)
+
+Allow a web server to bind to ports 80 and 443 without running as root:
+
+```conf
+service [2345] name:webserver \
+        @www-data:www-data \
+        caps:^cap_net_bind_service \
+        /usr/sbin/nginx -g 'daemon off;'
+```
+
+### Network Monitoring (Raw Sockets)
+
+Allow packet capture without root privileges:
+
+```conf
+service [2345] name:tcpdump \
+        @tcpdump \
+        caps:^cap_net_raw,^cap_net_admin \
+        /usr/sbin/tcpdump -i eth0 -w /var/log/capture.pcap
+```
+
+### NTP Daemon (System Time)
+
+Allow time synchronization without full root:
+
+```conf
+service [2345] name:ntpd \
+        @ntp \
+        caps:^cap_sys_time,^cap_sys_nice \
+        /usr/sbin/ntpd -n
+```
+
+## Available Capabilities
+
+Common capabilities include (see `man 7 capabilities` for the complete list):
+
+- `cap_chown` - Make arbitrary changes to file UIDs and GIDs
+- `cap_dac_override` - Bypass file read, write, and execute permission checks
+- `cap_dac_read_search` - Bypass file read permission checks
+- `cap_fowner` - Bypass permission checks on operations that normally require filesystem UID
+- `cap_kill` - Bypass permission checks for sending signals
+- `cap_net_admin` - Perform various network-related operations
+- `cap_net_bind_service` - Bind to privileged ports (< 1024)
+- `cap_net_raw` - Use RAW and PACKET sockets
+- `cap_setgid` - Make arbitrary manipulations of process GIDs
+- `cap_setuid` - Make arbitrary manipulations of process UIDs
+- `cap_sys_admin` - Perform system administration operations (very powerful!)
+- `cap_sys_module` - Load and unload kernel modules
+- `cap_sys_nice` - Raise process nice value and change scheduling
+- `cap_sys_time` - Set system clock
+
+## Security Best Practices
+
+1. **Use the minimum required capabilities**
+   - Only grant what the service actually needs
+   - Don't grant `cap_sys_admin` unless absolutely necessary
+
+2. **Always specify a user**
+   - Always use `@user` to drop to a non-root user
+   - Capabilities work best when combined with user separation
+
+3. **Use ambient capabilities (`^`)**
+   - The `^` prefix ensures capabilities survive exec()
+   - Simpler than setting file capabilities on binaries
+
+4. **Block dangerous capabilities**
+   - Use `!` to explicitly block capabilities you don't want
+   - Example: `!cap_sys_admin,!cap_sys_module`
+
+5. **Test with `getpcaps`**
+   - After starting a service, verify its capabilities:
+     ```bash
+     getpcaps $(pidof nginx)
+     ```
+   - Should show only the capabilities you granted
+
+## Verification
+
+After configuring a service with capabilities, verify it works correctly:
+
+```bash
+# Start the service
+initctl start webserver
+
+# Check the process capabilities
+getpcaps $(pidof nginx)
+
+# Should show something like:
+# 12345: cap_net_bind_service=eip
+
+# Verify the user
+ps -o user,pid,cmd -p $(pidof nginx)
+
+# Should show the service running as the specified user
+```
+
+## Requirements
+
+- Linux kernel 4.3+ (for ambient capabilities support)
+- libcap library installed
+- Finit built with `--enable-libcap`
+
+## Limitations
+
+- Capabilities are only applied when both `@user` and `caps:` are specified
+- The service must drop to a non-root user for capabilities to be effective
+- Some very old binaries may not work correctly with ambient capabilities
+- File system capabilities are not managed by Finit (use `setcap` for that)
+
+## See Also
+
+- `man 7 capabilities` - Linux capabilities overview
+- `man 3 cap_iab` - IAB capability API documentation
+- `man 8 setcap` - Set file capabilities
+- `man 8 getcap` - Query file capabilities
+- `man 1 capsh` - Capability shell wrapper

doc/config/service-opts.md

@@ -42,6 +42,7 @@ started at any time by running `initctl start <service>`.
 
 Other run/task/service options are:
 
+  * `caps:...` -- see the [Linux Capabilities](capabilities.md) section
   * `cgroups:...` -- see the [Cgroups](cgroups.md) section
   * `env:[-]/path/to/env` -- see the [Service Environment](service-env.md) section
   * `log:...` -- see [Redirecting Output](logging.md#redirecting-output)

doc/features.md

@@ -130,6 +130,38 @@ unnecessary overhead, which can be removed at build-time using:
     configure --enable-auto-reload
 
 
+**Linux Capabilities**
+
+Finit supports Linux capabilities, allowing services to run with minimal
+required privileges instead of running as root. This improves security by
+following the principle of least privilege.
+
+```conf
+service [2345] name:nginx \
+        www-data:www-data \
+        caps:^cap_net_bind_service \
+        /usr/sbin/nginx -g 'daemon off;'
+```
+
+In this example, nginx runs as the unprivileged `www-data` user but retains
+the ability to bind to privileged ports (80, 443) through the
+`cap_net_bind_service` capability.
+
+The `caps:` directive uses the IAB (Inheritable, Ambient, Bounding) format:
+- `^` = Ambient (recommended) - capabilities survive exec()
+- `%` = Inheritable only - requires file capabilities
+- `!` = Bounding - block from acquiring capability
+
+Multiple capabilities can be specified as comma-separated:
+
+```conf
+caps:^cap_net_raw,^cap_net_admin,!cap_sys_admin
+```
+
+See the [Linux Capabilities](config/capabilities.md) section for detailed
+information, examples, and security best practices.
+
+
 **Cgroups**
 
 Finit supports cgroups v2 and comes with the following default groups in

src/service.c

@@ -39,6 +39,9 @@
 # include <lite/lite.h>
 #endif
 #include <wordexp.h>
+#ifdef HAVE_LIBCAP
+# include <sys/capability.h>
+#endif
 
 #include "cgroup.h"
 #include "client.h"
@@ -521,6 +524,36 @@ static void compose_cmdline(svc_t *svc, char *buf, size_t len)
 	}
 }
 
+static void set_uid(uid_t uid, svc_t *svc)
+{
+#ifdef HAVE_LIBCAP
+	if (cap_setuid(uid)) {
+		err(1, "%s: failed cap_setuid(%d)", svc_ident(svc, NULL, 0), uid);
+		return;
+	}
+
+	/* After dropping privileges, set the specific capabilities we need */
+	if (svc->capabilities[0]) {
+		cap_iab_t cap_iab = cap_iab_from_text(svc->capabilities);
+		if (!cap_iab) {
+			err(1, "%s: failed parsing capabilities '%s'",
+			    svc_ident(svc, NULL, 0), svc->capabilities);
+			return;
+		}
+
+		if (cap_iab_set_proc(cap_iab) != 0) {
+			cap_free(cap_iab);
+			err(1, "%s: failed setting capabilities",
+			    svc_ident(svc, NULL, 0));
+		}
+		cap_free(cap_iab);
+	}
+#else
+	if (setuid(uid))
+		err(1, "%s: failed setuid(%d)", svc_ident(svc, NULL, 0), uid);
+#endif
+}
+
 static pid_t service_fork(svc_t *svc)
 {
 	pid_t pid;
@@ -552,8 +585,7 @@ static pid_t service_fork(svc_t *svc)
 		}
 
 		if (uid >= 0) {
-			if (setuid(uid))
+			set_uid(uid, svc);
-				err(1, "%s: failed setuid(%d)", svc_ident(svc, NULL, 0), uid);
 
 			/* Set default path for regular users */
 			if (uid > 0)
@@ -1666,6 +1698,7 @@ int service_register(int type, char *cfg, struct rlimit rlimit[], char *file)
 	char *ready_script = NULL, *conflict = NULL;
 	char *reload_script = NULL, *stop_script = NULL;
 	char *cleanup_script = NULL;
+	char *caps = NULL;
 	char ident[MAX_IDENT_LEN];
 	char *ifstmt = NULL;
 	char *notify = NULL;
@@ -1781,6 +1814,8 @@ int service_register(int type, char *cfg, struct rlimit rlimit[], char *file)
 			stop_script = arg;
 		else if (MATCH_CMD(cmd, "env:", arg))
 			env = arg;
+		else if (MATCH_CMD(cmd, "caps:", arg))
+			caps = arg;
 		/* catch both cgroup: and cgroup. handled in parse_cgroup() */
 		else if (MATCH_CMD(cmd, "cgroup", arg))
 			cgroup = arg;
@@ -2004,6 +2039,10 @@ int service_register(int type, char *cfg, struct rlimit rlimit[], char *file)
 		parse_env(svc, env);
 	else
 		memset(svc->env, 0, sizeof(svc->env));
+	if (caps)
+		strlcpy(svc->capabilities, caps, sizeof(svc->capabilities));
+	else
+		memset(svc->capabilities, 0, sizeof(svc->capabilities));
 	if (file)
 		strlcpy(svc->file, file, sizeof(svc->file));
 	else

src/svc.h

@@ -191,6 +191,7 @@ typedef struct svc {
 	/* Identity */
 	char	       username[MAX_USER_LEN];
 	char	       group[MAX_USER_LEN];
+	char	       capabilities[MAX_CMD_LEN];
 
 	/* Command, arguments and service description */
 	char	       cmd[MAX_CMD_LEN];