Re: [PATCH v3 1/4] seccomp: Add sysctl to display available actions

[Kees Cook]

On Mon, Feb 13, 2017 at 7:45 PM, Tyler Hicks <tyhicks@xxxxxxxxxxxxx> wrote:
> This patch creates a read-only sysctl containing an ordered list of
> seccomp actions that the kernel supports. The ordering, from left to
> right, is the lowest action value (kill) to the highest action value
> (allow). Currently, a read of the sysctl file would return "kill trap
> errno trace allow". The contents of this sysctl file can be useful for
> userspace code as well as the system administrator.
>
> The path to the sysctl is:
>
>   /proc/sys/kernel/seccomp/actions_avail
>
> libseccomp and other userspace code can easily determine which actions
> the current kernel supports. The set of actions supported by the current
> kernel may be different than the set of action macros found in kernel
> headers that were installed where the userspace code was built.
>
> In addition, this sysctl will allow system administrators to know which
> actions are supported by the kernel and make it easier to configure
> exactly what seccomp logs through the audit subsystem. Support for this
> level of logging configuration will come in a future patch.
>
> Signed-off-by: Tyler Hicks <tyhicks@xxxxxxxxxxxxx>
> ---
>  Documentation/prctl/seccomp_filter.txt | 16 ++++++++++
>  Documentation/sysctl/kernel.txt        |  1 +
>  kernel/seccomp.c                       | 55 ++++++++++++++++++++++++++++++++++
>  3 files changed, 72 insertions(+)
>
> diff --git a/Documentation/prctl/seccomp_filter.txt b/Documentation/prctl/seccomp_filter.txt
> index 1e469ef..a5554ff 100644
> --- a/Documentation/prctl/seccomp_filter.txt
> +++ b/Documentation/prctl/seccomp_filter.txt
> @@ -166,7 +166,23 @@ 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.
>
>  Adding architecture support
>  -----------------------
> diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
> index a32b4b7..56f9b29 100644
> --- a/Documentation/sysctl/kernel.txt
> +++ b/Documentation/sysctl/kernel.txt
> @@ -74,6 +74,7 @@ show up in /proc/sys/kernel:
>  - reboot-cmd                  [ SPARC only ]
>  - rtsig-max
>  - rtsig-nr
> +- seccomp/                    ==> Documentation/prctl/seccomp_filter.txt
>  - sem
>  - sem_next_id                [ sysv ipc ]
>  - sg-big-buff                 [ generic SCSI device (sg) ]
> diff --git a/kernel/seccomp.c b/kernel/seccomp.c
> index f7ce79a..e36dfe9 100644
> --- a/kernel/seccomp.c
> +++ b/kernel/seccomp.c
> @@ -16,10 +16,12 @@
>  #include <linux/atomic.h>
>  #include <linux/audit.h>
>  #include <linux/compat.h>
> +#include <linux/kmemleak.h>
>  #include <linux/sched.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>
> @@ -905,3 +907,56 @@ 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_NAME          "kill"
> +#define SECCOMP_RET_TRAP_NAME          "trap"
> +#define SECCOMP_RET_ERRNO_NAME         "errno"
> +#define SECCOMP_RET_TRACE_NAME         "trace"
> +#define SECCOMP_RET_ALLOW_NAME         "allow"
> +
> +static char seccomp_actions_avail[] = SECCOMP_RET_KILL_NAME    " "
> +                                     SECCOMP_RET_TRAP_NAME     " "
> +                                     SECCOMP_RET_ERRNO_NAME    " "
> +                                     SECCOMP_RET_TRACE_NAME    " "
> +                                     SECCOMP_RET_ALLOW_NAME;
> +
> +static struct ctl_path seccomp_sysctl_path[] = {
> +       { .procname = "kernel", },
> +       { .procname = "seccomp", },
> +       { }
> +};
> +
> +static struct ctl_table seccomp_sysctl_table[] = {
> +       {
> +               .procname       = "actions_avail",
> +               .data           = &seccomp_actions_avail,
> +               .maxlen         = sizeof(seccomp_actions_avail),
> +               .mode           = 0444,
> +               .proc_handler   = proc_dostring,
> +       },
> +       { }
> +};
> +
> +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;
> +}
> +
> +#else /* CONFIG_SYSCTL */
> +
> +static __init int seccomp_sysctl_init(void) { return 0; }
> +
> +#endif /* CONFIG_SYSCTL */
> +
> +device_initcall(seccomp_sysctl_init)

Can the device_initcall() just live in the CONFIG_SYSCTL #ifdef to
avoid the #else and stub?

-Kees

-- 
Kees Cook
Pixel Security