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
---
include/sysemu/seccomp.h | 1 +
qemu-options.hx | 12 +---
qemu-seccomp.c | 11 +++
vl.c | 27 +++
4 files changed, 48 insertions(+), 3 deletions(-)
diff --git a/include/sysemu/seccomp.h b/include/sysemu/seccomp.h
index 215138a372..4a9e63c7cd 100644
--- a/include/sysemu/seccomp.h
+++ b/include/sysemu/seccomp.h
@@ -17,6 +17,7 @@
#define QEMU_SECCOMP_SET_DEFAULT (1 << 0)
#define QEMU_SECCOMP_SET_OBSOLETE(1 << 1)
+#define QEMU_SECCOMP_SET_PRIVILEGED (1 << 2)
#include
diff --git a/qemu-options.hx b/qemu-options.hx
index 72150c6b84..5c1b163fb5 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -4017,20 +4017,26 @@ Old param mode (ARM only).
ETEXI
DEF("sandbox", HAS_ARG, QEMU_OPTION_sandbox, \
-"-sandbox on[,obsolete=allow|deny]\n" \
+"-sandbox
on[,obsolete=allow|deny][,elevateprivileges=allow|deny|children]\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" \
-"C library implementations.\n",
+"C library implementations.\n" \
+"use 'elevateprivileges' to allow or deny QEMU process to
elevate\n" \
+"its privileges by blacklisting all set*uid|gid system
calls.\n" \
+"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",
QEMU_ARCH_ALL)
STEXI
-@item -sandbox @var{arg}[,obsolete=@var{string}]
+@item -sandbox
@var{arg}[,obsolete=@var{string}][,elevateprivileges=@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'.
@table @option
@item obsolete=@var{string}
Enable Obsolete system calls
+@item elevateprivileges=@var{string}
+Disable set*uid|gid system calls
@end table
ETEXI
diff --git a/qemu-seccomp.c b/qemu-seccomp.c
index 8a5fbd2ff1..978d66bd28 100644
--- a/qemu-seccomp.c
+++ b/qemu-seccomp.c
@@ -67,6 +67,17 @@ static const struct QemuSeccompSyscall blacklist[] = {
{ SCMP_SYS(sysfs), QEMU_SECCOMP_SET_OBSOLETE },
{ SCMP_SYS(uselib), QEMU_SECCOMP_SET_OBSOLETE },
{ SCMP_SYS(ustat), QEMU_SECCOMP_SET_OBSOLETE },
+/* privileged */
+{ SCMP_SYS(setuid), QEMU_SECCOMP_SET_PRIVILEGED },
+{ SCMP_SYS(setgid), QEMU_SECCOMP_SET_PRIVILEGED },
+{ SCMP_SYS(setpgid),QEMU_SECCOMP_SET_PRIVILEGED },
+{ SCMP_SYS(setsid), QEMU_SECCOMP_SET_PRIVILEGED },
+{ SCMP_SYS(setreuid), QEMU_SECCOMP_SET_PRIVILEGED },
+{ SCMP_SYS(setregid), QEMU_SECCOMP_SET_PRIVILEGED },
+{ SCMP_SYS(setresuid), QEMU_SECCOMP_SET_PRIVILEGED },
+{ SCMP_SYS(setresgid), QEMU_SECCOMP_SET_PRIVILEGED },
+{ SCMP_SYS(setfsuid), QEMU_SECCOMP_SET_PRIVILEGED },
+{ SCMP_SYS(setfsgid), QEMU_SECCOMP_SET_PRIVILEGED },
};
diff --git a/vl.c b/vl.c
index 62b71dd529..ff3b5c766a 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 */ }
},
};
@@ -1055,6 +1060,28 @@ 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
