On Mon, 18 May 2026 11:29:54 +0100
Pavel Begunkov <[email protected]> wrote:
> On 5/13/26 09:19, Christoph Hellwig wrote:
> >> + if (!bio_flagged(bio_src, BIO_DMABUF_MAP)) {
> >> + bio->bi_io_vec = bio_src->bi_io_vec;
> >> + } else {
> >> + bio->dmabuf_map = bio_src->dmabuf_map;
> >> + bio_set_flag(bio, BIO_DMABUF_MAP);
> >> + }
> >
> > This is backwards, please avoid pointless negations:
>
> I can flip it, but compilers tend to prefer the true branch. E.g. this
>
> if (cond) A; else B;
> C;
>
> can get compiled into:
>
> jmpcc cond B
> A: ...
> C:
> return;
> B: ...
> jmp C;
I'm pretty sure gcc completely ignores the order.
Some very old compilers didn't - to the extreme of generating a short
conditional branch around a long unconditional branch to get past a
large 'true' code block.
likely() and unlikely() can change things, they are definitely useful
comments to a human (or Human) reader.
I'm not sure you can rely on the branch predictor to do anything sensible
outside of a loop.
-- David
