On 02/13/2014 11:47 PM, H. Peter Anvin wrote:
On 02/13/2014 02:44 PM, Daniel Borkmann wrote:
quoted
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.
Really, I was under the impression there were. They *should be*, that
was an important concept in the development of the seccomp filters.
$ git grep -n BPF_S_ANC_SECCOMP_LD_W
include/linux/filter.h:153: BPF_S_ANC_SECCOMP_LD_W,
kernel/seccomp.c:136: ftest->code = BPF_S_ANC_SECCOMP_LD_W;
net/core/filter.c:389: case BPF_S_ANC_SECCOMP_LD_W:
net/core/filter.c:812: [BPF_S_ANC_SECCOMP_LD_W] = BPF_LD|BPF_B|BPF_ABS,
Afaik, there had been attempts to support it, but had flaws in it.
-hpa