Re: [GIT pull] perf/urgent for 5.7-rc2
From: Ingo Molnar
Date: Wed Apr 22 2020 - 03:45:18 EST
* Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> On Mon, Apr 20, 2020 at 09:48:45AM +0200, Ingo Molnar wrote:
> > Fortunately, much of what objtool does against vmlinux.o can be
> > parallelized in a rather straightforward fashion I believe, if we build
> > with -ffunction-sections.
>
> So that FGKASLR is going to get us -ffunction-sections, but
> parallelizing objtool isn't going to be trivial, it's data structures
> aren't really build for that, esp. decode_instructions() which actively
> generates data.
>
> Still, it's probably doable.
So AFAICS in the narrow code section I identified as the main overhead,
only the instruction hash needs threading, i.e. this step:
hash_add(file->insn_hash, &insn->hash, insn->offset);
list_add_tail(&insn->list, &file->insn_list);
Objtool can still be single-threaded before and after generating the
instruction hash.
99% of the overhead within decode_instructions() is in
arch_decode_instruction(), which is fully thread-safe AFAICS.
So the run time of objtool could be cut in ~third on most systems.
Thanks,
Ingo