Re: [PATCH RFC] seccomp: Implement syscall isolation based on memory areas

[Brendan Shanks]

> On May 31, 2020, at 11:57 AM, Andy Lutomirski <luto@xxxxxxxxxx> wrote:
> 
> Using SECCOMP_RET_USER_NOTIF is likely to be considerably more
> expensive than my scheme.  On a non-PTI system, my approach will add a
> few tens of ns to each syscall.  On a PTI system, it will be worse.
> But using any kind of notifier for all syscalls will cause a context
> switch to a different user program for each syscall, and that will be
> much slower.

Thereâs also no way (at least to my understanding) to modify register state from SECCOMP_RET_USER_NOTIF, which is how the existing -staging SIGSYS handler works:

<https://github.com/wine-staging/wine-staging/blob/master/patches/ntdll-Syscall_Emulation/0001-ntdll-Support-x86_64-syscall-emulation.patch#L62>

> I think that the implementation may well want to live in seccomp, but
> doing this as a seccomp filter isn't quite right.  It's not a security
> thing -- it's an emulation thing.  Seccomp is all about making
> inescapable sandboxes, but that's not what you're doing at all, and
> the fact that seccomp filters are preserved across execve() sounds
> like it'll be annoying for you.

Definitely. Regardless of what approach is taken, we donât want it to persist across execve.

> What if there was a special filter type that ran a BPF program on each
> syscall, and the program was allowed to access user memory to make its
> decisions, e.g. to look at some list of memory addresses.  But this
> would explicitly *not* be a security feature -- execve() would remove
> the filter, and the filter's outcome would be one of redirecting
> execution or allowing the syscall.  If the "allow" outcome occurs,
> then regular seccomp filters run.  Obviously the exact semantics here
> would need some care.

Although if thatâs running a BPF filter on every syscall, wouldnât it also incur the ~10% overhead that Paul and Gabriel have seen with existing seccomp?


Brendan Shanks
CodeWeavers