seccomp: add elevateprivileges argument to command line

This patch introduces the new argument
[,elevateprivileges=allow|deny|children] to the `-sandbox on'. It allows
or denies Qemu process to elevate its privileges by blacklisting all
set*uid|gid system calls. The 'children' option will let forks and
execves run unprivileged.

Signed-off-by: Eduardo Otubo <otubo@redhat.com>

1 files changed, 27 insertions, 0 deletions

diff --git a/vl.c b/vl.c
index 57c5e93c1a..d59b560276 100644
--- a/vl.c
+++ b/vl.c
@@ -29,6 +29,7 @@
 
 #ifdef CONFIG_SECCOMP
 #include "sysemu/seccomp.h"
+#include "sys/prctl.h"
 #endif
 
 #if defined(CONFIG_VDE)
@@ -275,6 +276,10 @@ static QemuOptsList qemu_sandbox_opts = {
             .name = "obsolete",
             .type = QEMU_OPT_STRING,
         },
+        {
+            .name = "elevateprivileges",
+            .type = QEMU_OPT_STRING,
+        },
         { /* end of list */ }
     },
 };
@@ -1056,6 +1061,28 @@ static int parse_sandbox(void *opaque, QemuOpts *opts, Error **errp)
             }
         }
 
+        value = qemu_opt_get(opts, "elevateprivileges");
+        if (value) {
+            if (g_str_equal(value, "deny")) {
+                seccomp_opts |= QEMU_SECCOMP_SET_PRIVILEGED;
+            } else if (g_str_equal(value, "children")) {
+                seccomp_opts |= QEMU_SECCOMP_SET_PRIVILEGED;
+
+                /* calling prctl directly because we're
+                 * not sure if host has CAP_SYS_ADMIN set*/
+                if (prctl(PR_SET_NO_NEW_PRIVS, 1)) {
+                    error_report("failed to set no_new_privs "
+                                 "aborting");
+                    return -1;
+                }
+            } else if (g_str_equal(value, "allow")) {
+                /* default value */
+            } else {
+                error_report("invalid argument for elevateprivileges");
+                return -1;
+            }
+        }
+
         if (seccomp_start(seccomp_opts) < 0) {
             error_report("failed to install seccomp syscall filter "
                          "in the kernel");