[RFC 5/5] x86,seccomp: Add a seccomp fastpath

[Will Drewry]

On Wed, Jun 11, 2014 at 5:32 PM, Kees Cook <keescook at chromium.org> wrote:
> On Wed, Jun 11, 2014 at 3:28 PM, Andy Lutomirski <luto at amacapital.net> wrote:
>> On Wed, Jun 11, 2014 at 3:27 PM, H. Peter Anvin <hpa at zytor.com> wrote:
>>> On 06/11/2014 03:22 PM, Andy Lutomirski wrote:
>>>> On Wed, Jun 11, 2014 at 3:18 PM, H. Peter Anvin <hpa at zytor.com> wrote:
>>>>> On 06/11/2014 02:56 PM, Andy Lutomirski wrote:
>>>>>>
>>>>>> 13ns is with the simplest nonempty filter.  I hope that empty filters
>>>>>> don't work.
>>>>>>
>>>>>
>>>>> Why wouldn't they?
>>>>
>>>> Is it permissible to fall off the end of a BPF program?  I'm getting
>>>> EINVAL trying to install an actual empty filter.  The filter I tested
>>>> with was:
>>>>
>>>
>>> What I meant was that there has to be a well-defined behavior for the
>>> program falling off the end anyway, and that that should be preserved.
>>>
>>> I guess it is possible to require that all code paths must provably
>>> reach a termination point.
>>>
>>
>> Dunno.  I haven't ever touched any of the actual BPF code.  This whole
>> patchset only changes the code that invokes the BPF evaluator.
>
> Yes, this is how BPF works: runs to the end or exit early. With
> seccomp BPF specifically, the return value defaults to kill the
> process. If a filter was missing (NULL), or empty, or didn't
> explicitly return with a new value, the default (kill) should be
> taken.

Yup - this is just a property of BPF (and a nice one :)

On seccomp_attach_filter this check fires:
  if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
    return -EINVAL;

As well as in sk_chk_filter:
  if (flen == 0 || flen > BPF_MAXINSNS)
    return -EINVAL;

And:
  /* last instruction must be a RET code */
  switch (filter[flen - 1].code) {
    case BPF_S_RET_K:
    case BPF_S_RET_A:
      return check_load_and_stores(filter, flen);
  }

cheers!
will