From: "H.J. Lu" <hjl.tools@gmail.com>
To: Arjan van de Ven <arjan@linux.intel.com>
Cc: Andreas Schwab <schwab@linux-m68k.org>,
Arjan van de Ven via Libc-alpha <libc-alpha@sourceware.org>,
Oleh Derevenko <oleh.derevenko@gmail.com>
Subject: Re: [PATCH] x86: Optimize atomic_compare_and_exchange_[val|bool]_acq [BZ #28537]
Date: Wed, 3 Nov 2021 12:48:39 -0700 [thread overview]
Message-ID: <CAMe9rOqDJb7mHCotRbCGBpJGXw0u3b3-SwqNCrG6pPyrHndNpg@mail.gmail.com> (raw)
In-Reply-To: <f51d7521-7ee9-9978-6219-6f87afa54b38@linux.intel.com>
On Wed, Nov 3, 2021 at 12:21 PM Arjan van de Ven <arjan@linux.intel.com> wrote:
>
> On 11/3/2021 10:17 AM, Andreas Schwab wrote:
> > On Nov 03 2021, Arjan van de Ven via Libc-alpha wrote:
> >
> >> What the patch does is check non-atomic first if the actual atomic operation has
> >> a chance of working. if it has a chance, the actual normal atomic operation is done as
> >> before. But if non-atomic read already tells you the cmpxchg has no chance to succeed, it errors
> >> out early.
> >
> > But if the compiler keeps reusing the same cached value it may conclude
> > that the CAS _never_ has a chance to succeed.
>
> that's a good point. Now there SHOULD be a (compiler) barrier around this somewhere due
> to inserting the pause instruction for such a loop. But putting some explicit compiler barrier in this
> makes it for sure safer.
Like this?
#define atomic_compare_and_exchange_val_acq(mem, newval, oldval) \
({ __typeof (*(mem)) oldmem = *(mem), ret; \
atomic_read_barrier (); \
ret = (oldmem == (oldval) \
? __sync_val_compare_and_swap (mem, oldval, newval) \
: oldmem); \
ret; })
#define atomic_compare_and_exchange_bool_acq(mem, newval, oldval) \
({ __typeof (*(mem)) oldmem = *(mem); \
atomic_read_barrier (); \
int ret; \
ret = (oldmem == (oldval) \
? !__sync_bool_compare_and_swap (mem, oldval, newval) \
: 1); \
ret; })
--
H.J.
next prev parent reply other threads:[~2021-11-03 19:49 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-03 15:04 H.J. Lu
2021-11-03 15:14 ` Andreas Schwab
2021-11-03 15:50 ` Oleh Derevenko
2021-11-03 16:59 ` Arjan van de Ven
2021-11-03 17:17 ` Andreas Schwab
2021-11-03 19:21 ` Arjan van de Ven
2021-11-03 19:48 ` H.J. Lu [this message]
2021-11-03 20:38 ` Oleh Derevenko
2021-11-03 22:12 ` H.J. Lu
2021-11-04 8:58 ` Oleh Derevenko
2021-11-04 9:44 ` Oleh Derevenko
2021-11-03 17:26 ` Oleh Derevenko
2021-11-03 17:30 ` Arjan van de Ven
2021-11-03 17:55 ` Oleh Derevenko
2021-11-03 19:22 ` Arjan van de Ven
2021-11-04 11:42 ` Oleh Derevenko
2021-11-04 14:15 ` Arjan van de Ven
2021-11-03 16:35 ` Florian Weimer
2021-11-03 19:13 ` H.J. Lu
2021-11-04 10:15 ` Florian Weimer
2021-11-04 14:31 ` H.J. Lu
2021-11-04 14:59 ` H.J. Lu
2021-11-03 17:25 ` Noah Goldstein
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=CAMe9rOqDJb7mHCotRbCGBpJGXw0u3b3-SwqNCrG6pPyrHndNpg@mail.gmail.com \
--to=hjl.tools@gmail.com \
--cc=arjan@linux.intel.com \
--cc=libc-alpha@sourceware.org \
--cc=oleh.derevenko@gmail.com \
--cc=schwab@linux-m68k.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 read-only IMAP folder(s) and NNTP newsgroup(s).