seccomp: add resourcecontrol argument to command line

This patch adds [,resourcecontrol=deny] to `-sandbox on' option. It
blacklists all process affinity and scheduler priority system calls to
avoid any bigger of the process.

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

include/sysemu/seccomp.h

@@ -19,6 +19,7 @@
 #define QEMU_SECCOMP_SET_OBSOLETE    (1 << 1)
 #define QEMU_SECCOMP_SET_PRIVILEGED  (1 << 2)
 #define QEMU_SECCOMP_SET_SPAWN       (1 << 3)
+#define QEMU_SECCOMP_SET_RESOURCECTL (1 << 4)
 
 #include <seccomp.h>
 

qemu-options.hx

@@ -4018,7 +4018,7 @@ ETEXI
 
 DEF("sandbox", HAS_ARG, QEMU_OPTION_sandbox, \
     "-sandbox on[,obsolete=allow|deny][,elevateprivileges=allow|deny|children]\n" \
-    "          [,spawn=allow|deny]\n" \
+    "          [,spawn=allow|deny][,resourcecontrol=allow|deny]\n" \
     "                Enable seccomp mode 2 system call filter (default 'off').\n" \
     "                use 'obsolete' to allow obsolete system calls that are provided\n" \
     "                    by the kernel, but typically no longer used by modern\n" \
@@ -4028,10 +4028,11 @@ DEF("sandbox", HAS_ARG, QEMU_OPTION_sandbox, \
     "                    The value 'children' will deny set*uid|gid system calls for\n" \
     "                    main QEMU process but will allow forks and execves to run unprivileged\n" \
     "                use 'spawn' to avoid QEMU to spawn new threads or processes by\n" \
-    "                     blacklisting *fork and execve\n",
+    "                     blacklisting *fork and execve\n" \
+    "                use 'resourcecontrol' to disable process affinity and schedular priority\n",
     QEMU_ARCH_ALL)
 STEXI
-@item -sandbox @var{arg}[,obsolete=@var{string}][,elevateprivileges=@var{string}][,spawn=@var{string}]
+@item -sandbox @var{arg}[,obsolete=@var{string}][,elevateprivileges=@var{string}][,spawn=@var{string}][,resourcecontrol=@var{string}]
 @findex -sandbox
 Enable Seccomp mode 2 system call filter. 'on' will enable syscall filtering and 'off' will
 disable it.  The default is 'off'.
@@ -4042,6 +4043,8 @@ Enable Obsolete system calls
 Disable set*uid|gid system calls
 @item spawn=@var{string}
 Disable *fork and execve
+@item resourcecontrol=@var{string}
+Disable process affinity and schedular priority
 @end table
 ETEXI
 

qemu-seccomp.c

@@ -82,6 +82,17 @@ static const struct QemuSeccompSyscall blacklist[] = {
     { SCMP_SYS(fork),                   QEMU_SECCOMP_SET_SPAWN },
     { SCMP_SYS(vfork),                  QEMU_SECCOMP_SET_SPAWN },
     { SCMP_SYS(execve),                 QEMU_SECCOMP_SET_SPAWN },
+    /* resource control */
+    { SCMP_SYS(getpriority),            QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(setpriority),            QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_setparam),         QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_getparam),         QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_setscheduler),     QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_getscheduler),     QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_setaffinity),      QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_getaffinity),      QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_get_priority_max), QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_get_priority_min), QEMU_SECCOMP_SET_RESOURCECTL },
 };
 
 

vl.c

@@ -284,6 +284,10 @@ static QemuOptsList qemu_sandbox_opts = {
             .name = "spawn",
             .type = QEMU_OPT_STRING,
         },
+        {
+            .name = "resourcecontrol",
+            .type = QEMU_OPT_STRING,
+        },
         { /* end of list */ }
     },
 };
@@ -1099,6 +1103,18 @@ static int parse_sandbox(void *opaque, QemuOpts *opts, Error **errp)
             }
         }
 
+        value = qemu_opt_get(opts, "resourcecontrol");
+        if (value) {
+            if (g_str_equal(value, "deny")) {
+                seccomp_opts |= QEMU_SECCOMP_SET_RESOURCECTL;
+            } else if (g_str_equal(value, "allow")) {
+                /* default value */
+            } else {
+                error_report("invalid argument for resourcecontrol");
+                return -1;
+            }
+        }
+
         if (seccomp_start(seccomp_opts) < 0) {
             error_report("failed to install seccomp syscall filter "
                          "in the kernel");