From: Nick Desaulniers <ndesaulniers@google.com>
To: Linus Torvalds <torvalds@linux-foundation.org>,
Masahiro Yamada <masahiroy@kernel.org>
Cc: Kees Cook <keescook@chromium.org>,
Josef Bacik <josef@toxicpanda.com>, Jens Axboe <axboe@kernel.dk>,
Rasmus Villemoes <linux@rasmusvillemoes.dk>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Sasha Levin <sashal@kernel.org>,
llvm@lists.linux.dev, stable <stable@vger.kernel.org>,
Arnd Bergmann <arnd@kernel.org>,
Naresh Kamboju <naresh.kamboju@linaro.org>,
Nathan Chancellor <nathan@kernel.org>,
Stephen Rothwell <sfr@canb.auug.org.au>,
Pavel Machek <pavel@ucw.cz>
Subject: Re: [PATCH 5.10] overflow.h: use new generic division helpers to avoid / operator
Date: Tue, 14 Sep 2021 12:12:41 -0700 [thread overview]
Message-ID: <CAKwvOdnYdhkiYZdRvJSzAA78bMD3aS9oayc4SeeANddgxUsMLQ@mail.gmail.com> (raw)
In-Reply-To: <CAHk-=whU_p489R+ZYPh_AehJRQJKp_0oJ3zB73wgCtB_k3vwvA@mail.gmail.com>
On Tue, Sep 14, 2021 at 11:55 AM Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> Btw, these kinds of issues is exactly why I've been hardnosed about
> 64-bit divides for decades. 64-bit divides on 32-bit machines are
> *expensive*. It's why I don't like saying "just use '/' and we'll pick
> up the routines from libgcc".
I was going to ask about the history there; not to derail the thread
further, but this is a question whose answer is important to me.
Are the helpers from libgcc insufficient? Working through
https://github.com/ClangBuiltLinux/linux/issues/1438 which all came
about because LLVM's equivalent of libgcc, "compiler-rt," had a nice
helper for builtin multiply with overflow check that libgcc does not.
As such, llvm cannot assume compiler-rt is being linked against, so
llvm must expand these inline every time. And the code in line is
HUGE: https://godbolt.org/z/MM4hPGxTE. IMO we could do a much much
better job on code size (and thus probably I$ performance
improvements) had we just linked against the compiler runtime.
Perhaps the concern is of the quality of implementations of the
compiler runtime routines; that we may have arch specific
implementations that are better? 64b division on 32b targets is
expensive either way; I'd rather have the compiler generate a libcall
than try to expand these inline. I'm not sure if it's the case, but I
can't help but wonder if there are other optimization decisions being
based on whether the compiler runtime is being linked against or not;
it's hard for the compiler to know what will happen at link time.
Vaguely reminiscent of the issues we face against using
-ffreestanding.
Switching that now (so that we did link in the compiler runtimes)
would be a massive yak shave, for sure.
> In almost all real-life cases - at least in a kernel - the full divide
> is unnecessary. It's almost always people being silly and lazy, and
> the very expensive operation can be avoided entirely (or at least
> minimized to something like 64/32).
At least when dealing in powers of two, sure.
--
Thanks,
~Nick Desaulniers
next prev parent reply other threads:[~2021-09-14 19:14 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-13 20:32 [PATCH 5.10] overflow.h: use new generic division helpers to avoid / operator Nick Desaulniers
2021-09-13 21:05 ` Rasmus Villemoes
2021-09-14 0:23 ` [PATCH v2] " Nick Desaulniers
2021-09-14 17:22 ` Greg Kroah-Hartman
2021-09-14 18:07 ` Nick Desaulniers
2021-09-14 18:12 ` Greg Kroah-Hartman
2021-09-14 17:32 ` [PATCH 5.10] " Kees Cook
2021-09-14 18:14 ` Linus Torvalds
2021-09-14 18:30 ` Linus Torvalds
2021-09-14 18:44 ` Nick Desaulniers
2021-09-14 18:48 ` Linus Torvalds
2021-09-14 18:56 ` Linus Torvalds
2021-09-14 19:10 ` Nick Desaulniers
2021-09-14 19:45 ` Linus Torvalds
2021-09-14 19:50 ` Nick Desaulniers
2021-09-14 19:57 ` Linus Torvalds
2021-09-14 18:47 ` Kees Cook
2021-09-14 18:54 ` Linus Torvalds
2021-09-14 19:12 ` Nick Desaulniers [this message]
2021-09-14 19:52 ` Linus Torvalds
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAKwvOdnYdhkiYZdRvJSzAA78bMD3aS9oayc4SeeANddgxUsMLQ@mail.gmail.com \
--to=ndesaulniers@google.com \
--cc=arnd@kernel.org \
--cc=axboe@kernel.dk \
--cc=gregkh@linuxfoundation.org \
--cc=josef@toxicpanda.com \
--cc=keescook@chromium.org \
--cc=linux@rasmusvillemoes.dk \
--cc=llvm@lists.linux.dev \
--cc=masahiroy@kernel.org \
--cc=naresh.kamboju@linaro.org \
--cc=nathan@kernel.org \
--cc=pavel@ucw.cz \
--cc=sashal@kernel.org \
--cc=sfr@canb.auug.org.au \
--cc=stable@vger.kernel.org \
--cc=torvalds@linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).