From: Jeremy Fitzhardinge <jeremy@goop.org>
To: Peter Zijlstra <peterz@infradead.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@elte.hu>,
the arch/x86 maintainers <x86@kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Nick Piggin <npiggin@kernel.dk>,
Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>,
Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [PATCH RFC 0/7] x86: convert ticketlocks to C and remove duplicate code
Date: Wed, 22 Jun 2011 12:21:16 -0700 [thread overview]
Message-ID: <4E0240AC.9060603@goop.org> (raw)
In-Reply-To: <1308664868.26237.173.camel@twins>
On 06/21/2011 07:01 AM, Peter Zijlstra wrote:
> One other thing you could contemplate is adding something like:
>
> #define xadd(ptr, inc) \
> do { \
> switch(sizeof(*(ptr))) { \
> case 1: \
> asm volatile (LOCK_PREFIX "xaddb %0, %1\n" \
> : "+r" (inc), "+m" (*(ptr)) \
> : : "memory", "cc"); \
> case 2:
> ... xaddw ...
> case 4:
> ... xaddl ...
> } while (0)
>
> and a similar something for inc. For both there seem to be various asm
> bits left (we could even consider adding xadd to
> arch/x86/include/asm/cmpxchg*.h).
A friend just pointed out that gcc has a "__sync_fetch_and_add()"
intrinsic, which compiles to xadd when used in this context. What's the
general feeling about using these kinds of gcc features?
It also has __sync_bool_compare_and_swap(), which would simplify a lot
of asm/cmpxchg.h...
J
next prev parent reply other threads:[~2011-06-22 19:40 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-06-16 21:40 [PATCH RFC 0/7] x86: convert ticketlocks to C and remove duplicate code Jeremy Fitzhardinge
2011-06-16 21:40 ` [PATCH 1/7] x86/ticketlock: clean up types and accessors Jeremy Fitzhardinge
2011-06-16 21:40 ` [PATCH 2/7] x86/ticketlock: convert spin loop to C Jeremy Fitzhardinge
2011-06-16 21:40 ` [PATCH 3/7] x86/ticketlock: Use C for __ticket_spin_unlock Jeremy Fitzhardinge
2011-06-16 21:40 ` [PATCH 4/7] x86/ticketlock: make large and small ticket versions of spin_lock the same Jeremy Fitzhardinge
2011-06-16 21:40 ` [PATCH 5/7] x86/ticketlock: make __ticket_spin_lock common Jeremy Fitzhardinge
2011-06-16 21:40 ` [PATCH 6/7] x86/ticketlock: make __ticket_spin_trylock common Jeremy Fitzhardinge
2011-06-16 21:40 ` [PATCH 7/7] x86/ticketlock: prevent memory accesses from reordered out of lock region Jeremy Fitzhardinge
2011-06-21 14:01 ` [PATCH RFC 0/7] x86: convert ticketlocks to C and remove duplicate code Peter Zijlstra
2011-06-21 17:54 ` Jeremy Fitzhardinge
2011-06-22 19:21 ` Jeremy Fitzhardinge [this message]
2011-06-22 20:19 ` H. Peter Anvin
2011-06-22 20:59 ` Jeremy Fitzhardinge
2011-06-22 21:07 ` H. Peter Anvin
2011-06-22 21:35 ` Jeremy Fitzhardinge
2011-06-22 23:16 ` H. Peter Anvin
2011-06-21 14:18 ` Konrad Rzeszutek Wilk
2011-06-24 1:19 ` [PATCH 1/8] x86/ticketlock: clean up types and accessors Jeremy Fitzhardinge
2011-06-24 1:19 ` [PATCH 2/8] x86/ticketlock: convert spin loop to C Jeremy Fitzhardinge
2011-07-22 19:55 ` [tip:x86/spinlocks] x86, ticketlock: Convert " tip-bot for Jeremy Fitzhardinge
2011-06-24 1:19 ` [PATCH 3/8] x86/ticketlock: Use C for __ticket_spin_unlock Jeremy Fitzhardinge
2011-06-24 21:52 ` H. Peter Anvin
2011-06-24 22:41 ` Jeremy Fitzhardinge
2011-07-22 18:32 ` H. Peter Anvin
2011-07-22 19:28 ` Jeremy Fitzhardinge
2011-07-22 19:56 ` [tip:x86/spinlocks] x86, ticketlock: Use asm volatile for __ticket_unlock_release() tip-bot for H. Peter Anvin
2011-07-22 19:56 ` [tip:x86/spinlocks] x86, ticketlock: Use C for __ticket_spin_unlock tip-bot for Jeremy Fitzhardinge
2011-06-24 1:19 ` [PATCH 4/8] x86/ticketlock: make large and small ticket versions of spin_lock the same Jeremy Fitzhardinge
2011-07-22 19:57 ` [tip:x86/spinlocks] x86, ticketlock: Make " tip-bot for Jeremy Fitzhardinge
2011-06-24 1:19 ` [PATCH 5/8] x86/ticketlock: make __ticket_spin_lock common Jeremy Fitzhardinge
2011-07-22 19:57 ` [tip:x86/spinlocks] x86, ticketlock: Make " tip-bot for Jeremy Fitzhardinge
2011-06-24 1:19 ` [PATCH 6/8] x86/ticketlock: make __ticket_spin_trylock common Jeremy Fitzhardinge
2011-07-22 19:57 ` [tip:x86/spinlocks] x86, ticketlock: Make " tip-bot for Jeremy Fitzhardinge
2011-06-24 1:19 ` [PATCH 7/8] x86: add xadd helper macro Jeremy Fitzhardinge
2011-07-22 19:58 ` [tip:x86/spinlocks] x86: Add " tip-bot for Jeremy Fitzhardinge
2011-06-24 1:19 ` [PATCH 8/8] x86/ticketlock: use xadd helper Jeremy Fitzhardinge
2011-07-22 19:58 ` [tip:x86/spinlocks] x86, ticketlock: Use " tip-bot for Jeremy Fitzhardinge
2011-07-22 19:55 ` [tip:x86/spinlocks] x86, ticketlock: Clean up types and accessors tip-bot for Jeremy Fitzhardinge
2011-06-24 21:50 ` [PATCH RFC 0/7] x86: convert ticketlocks to C and remove duplicate code H. Peter Anvin
2011-06-24 22:42 ` Jeremy Fitzhardinge
2011-06-25 3:15 ` H. Peter Anvin
2011-07-15 17:24 ` Jeremy Fitzhardinge
2011-07-15 23:06 ` H. Peter Anvin
2011-07-16 0:14 ` Jeremy Fitzhardinge
2011-06-25 10:11 ` Ingo Molnar
2011-06-29 20:44 ` Andi Kleen
2011-07-21 23:33 ` Jeremy Fitzhardinge
2011-07-22 16:25 ` Andi Kleen
2011-09-07 23:25 ` Jeremy Fitzhardinge
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=4E0240AC.9060603@goop.org \
--to=jeremy@goop.org \
--cc=hpa@zytor.com \
--cc=jeremy.fitzhardinge@citrix.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=npiggin@kernel.dk \
--cc=peterz@infradead.org \
--cc=torvalds@linux-foundation.org \
--cc=x86@kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.