On Fri, Jul 28, 2017 at 02:10:36PM +0200, Eduardo Otubo wrote:
> This patch introduces the argument [,obsolete=allow] to the `-sandbox on'
> option. It allows Qemu to run safely on old system that still relies on
> old system calls.
>
> Signed-off-by: Eduardo Otubo <ot...@redhat.com>
> ---
> include/sysemu/seccomp.h | 4 +++-
> qemu-options.hx | 9 +++++++--
> qemu-seccomp.c | 32 +++++++++++++++++++++++++++++++-
> vl.c | 16 +++++++++++++++-
> 4 files changed, 56 insertions(+), 5 deletions(-)
>
> diff --git a/include/sysemu/seccomp.h b/include/sysemu/seccomp.h
> index cfc06008cb..7a7bde246b 100644
> --- a/include/sysemu/seccomp.h
> +++ b/include/sysemu/seccomp.h
> @@ -15,7 +15,9 @@
> #ifndef QEMU_SECCOMP_H
> #define QEMU_SECCOMP_H
>
> +#define OBSOLETE 0x0001
Please namespace this - its far too generic a term to expose to other
source files. I'd suggest
QEMU_SECCOMP_SET_OBSOLETE
> -int seccomp_start(void);
> +int seccomp_start(uint8_t seccomp_opts);
This only allows for 8 sets. Perhaps its enough, but I'd suggest
just using a uint32_t straight away.
> diff --git a/qemu-options.hx b/qemu-options.hx
> index 746b5fa75d..54e492f36a 100644
> --- a/qemu-options.hx
> +++ b/qemu-options.hx
> @@ -4004,13 +4004,18 @@ Old param mode (ARM only).
> ETEXI
>
> DEF("sandbox", HAS_ARG, QEMU_OPTION_sandbox, \
> - "-sandbox <arg> Enable seccomp mode 2 system call filter (default
> 'off').\n",
> + "-sandbox on[,obsolete=allow] Enable seccomp mode 2 system call filter
> (default 'off').\n" \
> + " obsolete: Allow obsolete system calls\n",
> QEMU_ARCH_ALL)
> STEXI
> -@item -sandbox @var{arg}
> +@item -sandbox @var{arg}[,obsolete=@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
Lets explain this a bit more.
E obsolete system calls that are provided by the kernel, but typically no
longer used by modern C library implementations.
> +@end table
> ETEXI
>
> DEF("readconfig", HAS_ARG, QEMU_OPTION_readconfig,
> diff --git a/qemu-seccomp.c b/qemu-seccomp.c
> index f8877b07b5..c6a8b28260 100644
> --- a/qemu-seccomp.c
> +++ b/qemu-seccomp.c
> @@ -31,6 +31,20 @@ struct QemuSeccompSyscall {
> uint8_t priority;
> };
>
> +static const struct QemuSeccompSyscall obsolete[] = {
> + { SCMP_SYS(readdir), 255 },
> + { SCMP_SYS(_sysctl), 255 },
> + { SCMP_SYS(bdflush), 255 },
> + { SCMP_SYS(create_module), 255 },
> + { SCMP_SYS(get_kernel_syms), 255 },
> + { SCMP_SYS(query_module), 255 },
> + { SCMP_SYS(sgetmask), 255 },
> + { SCMP_SYS(ssetmask), 255 },
> + { SCMP_SYS(sysfs), 255 },
> + { SCMP_SYS(uselib), 255 },
> + { SCMP_SYS(ustat), 255 },
> +};
> +
> static const struct QemuSeccompSyscall blacklist[] = {
> { SCMP_SYS(reboot), 255 },
> { SCMP_SYS(swapon), 255 },
> @@ -56,7 +70,20 @@ static const struct QemuSeccompSyscall blacklist[] = {
> { SCMP_SYS(vserver), 255 },
> };
>
> -int seccomp_start(void)
> +static int is_obsolete(int syscall)
> +{
> + unsigned int i = 0;
> +
> + for (i = 0; i < ARRAY_SIZE(obsolete); i++) {
> + if (syscall == obsolete[i].num) {
> + return 1;
> + }
> + }
> +
> + return 0;
> +}
> +
> +int seccomp_start(uint8_t seccomp_opts)
> {
> int rc = 0;
> unsigned int i = 0;
> @@ -69,6 +96,9 @@ int seccomp_start(void)
> }
>
> for (i = 0; i < ARRAY_SIZE(blacklist); i++) {
> + if ((seccomp_opts & OBSOLETE) && is_obsolete(blacklist[i].num)) {
> + continue;
> + }
IMHO this is leading to a rather inefficient approach. Why not extend
QemuSeccompSyscall struct so that it has another field to list which
set it belongs to. Then you can do
static const struct QemuSeccompSyscall blacklist[] = {
{ SCMP_SYS(reboot), 255, QEMU_SECCOMP_SET_DEFAULT },
{ SCMP_SYS(swapon), 255, QEMU_SECCOMP_SET_DEFAULT },
....
{ SCMP_SYS(readdir), 255, QEMU_SECCOMP_SET_OBSOLETE },
{ SCMP_SYS(_sysctl), 255, QEMU_SECCOMP_SET_OBSOLETE },
...
And then to process this you can do
for (i = 0; i < ARRAY_SIZE(blacklist); i++) {
if (blacklist[i].set != QEMU_SECCOMP_SET_OBSOLETE &&
blacklist[i].set & seccomp_opts) {
continue;
}
> rc = seccomp_rule_add(ctx, SCMP_ACT_KILL, blacklist[i].num, 0);
> if (rc < 0) {
> goto seccomp_return;
> diff --git a/vl.c b/vl.c
> index 15b98800e9..cbe09c94af 100644
> --- a/vl.c
> +++ b/vl.c
> @@ -271,6 +271,10 @@ static QemuOptsList qemu_sandbox_opts = {
> .name = "enable",
> .type = QEMU_OPT_BOOL,
> },
> + {
> + .name = "obsolete",
> + .type = QEMU_OPT_STRING,
> + },
> { /* end of list */ }
> },
> };
> @@ -1032,7 +1036,17 @@ static int parse_sandbox(void *opaque, QemuOpts *opts,
> Error **errp)
> {
> if (qemu_opt_get_bool(opts, "enable", false)) {
> #ifdef CONFIG_SECCOMP
> - if (seccomp_start() < 0) {
> + uint8_t seccomp_opts = 0x0000;
> + const char *value = NULL;
> +
> + value = qemu_opt_get(opts, "obsolete");
> + if (value) {
> + if (strcmp(value, "allow") == 0) {
> + seccomp_opts |= OBSOLETE;
> + }
> + }
IIUC, the values will all be booleans, so we should just use
if (qemu_opt_get_bool(opts, "obsolete", false))
seccomp_opts |= OBSOLETE;
> +
> + if (seccomp_start(seccomp_opts) < 0) {
> error_report("failed to install seccomp syscall filter "
> "in the kernel");
> return -1;
Regards,
Daniel
--
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :|
|: https://libvirt.org -o- https://fstop138.berrange.com :|
|: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
