[lkml]   [2014]   [Feb]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [RFC PATCH v2 tip 0/7] 64-bit BPF insn set and tracing filters
On 02/13/2014 11:32 PM, H. Peter Anvin wrote:
> On 02/06/2014 05:20 PM, Alexei Starovoitov wrote:
>> I believe that old BPF outlived itself and BPF64 should
>> replace it in all current use cases plus a lot more.
>> It just cannot happen at once.
>> BPF64 can come in. bpf32->bpf64 converter functioning.
>> JIT from bpf64->aarch64 and may be sparc64 needs to be in place.
>> Then old bpf can fade away.
> I don't think that is doable any time soon. Right now pretty much all
> mobile devices, for example, are 32 bits and they really want to use
> syscall filtering for security. Performance matters greatly there.

Well, if that would be the case, then seccomp would have had JIT support
long ago. ;-) Right now BPF filters with seccomp are not JIT compiled
for _any_ architecture.

> As such, 32-bit JIT support is going to be very important for a long
> time to come.

True, I think that pretty much depends if we can manage to find a way
to cleanly integrate it into net/core/filter.c while still supporting
the old instructions as I've mentioned earlier.

> -hpa

 \ /
  Last update: 2014-02-14 00:21    [W:0.071 / U:0.688 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site