On 01/28/2018 07:58 PM, Naveen N. Rao wrote: > in 32 bit alu > > Daniel Borkmann wrote: >> Very minor optimization; saves 1 byte per program in x86_64 >> JIT in cBPF prologue. > > ... but increases program size by 4 bytes on ppc64 :( > In general, this is an area I've been wanting to spend some time on. Powerpc > doesn't have 32-bit sub-registers, so we need to emit an additional > instruction to clear the higher 32-bits for all 32-bit operations. I need to > look at the performance impact.
Right, I think one way to optimize this could be on JIT level in such case when CPU doesn't have subregs. There is the bpf_prog_was_classic() helper that can be used there in order to skip some of the bpf_alu32_trunc goto cases e.g. for some of the bit ops as an example, since we know that upper part in cBPF must be zero here anyway, this should definitely be a low hanging fruit given we use alu32 in the cBPF to eBPF conversion in a lot of places. Thanks, Daniel
