[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20160601140628.GD355@arm.com>
Date: Wed, 1 Jun 2016 15:06:29 +0100
From: Will Deacon <will.deacon@....com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: torvalds@...ux-foundation.org, mingo@...nel.org,
tglx@...utronix.de, paulmck@...ux.vnet.ibm.com,
boqun.feng@...il.com, waiman.long@....com, fweisbec@...il.com,
linux-kernel@...r.kernel.org, linux-arch@...r.kernel.org,
rth@...ddle.net, vgupta@...opsys.com, linux@....linux.org.uk,
egtvedt@...fundet.no, realmz6@...il.com,
ysato@...rs.sourceforge.jp, rkuo@...eaurora.org,
tony.luck@...el.com, geert@...ux-m68k.org, james.hogan@...tec.com,
ralf@...ux-mips.org, dhowells@...hat.com, jejb@...isc-linux.org,
mpe@...erman.id.au, schwidefsky@...ibm.com, dalias@...c.org,
davem@...emloft.net, cmetcalf@...lanox.com, jcmvbkbc@...il.com,
arnd@...db.de, dbueso@...e.de, fengguang.wu@...el.com
Subject: Re: [PATCH -v2 00/33] implement atomic_fetch_$op
On Tue, May 31, 2016 at 12:19:25PM +0200, Peter Zijlstra wrote:
> As there have been a few requests for atomic_fetch_$op primitives and recently
> by Linus, I figured I'd go and implement the lot.
>
> The atomic_fetch_$op differs from the existing atomic_$op_return we already
> have by returning the old value instead of the new value. This is especially
> useful when the operation is irreversible (like bitops), and allows for things
> like test-and-set.
>
> This version incorporates all feedback from last time and is now complete thanks
> to Will implementing ARMv8.1-LSE versions.
>
> No known build breakage from the build-bot.
>
> Notes:
> - arc asm/atomic.h is a bit of a mess after the eznps merge, I would
> recommend a restructure or split of that file, but could not find
> the will to do it.
> - arc, metag and tile could convert to _relaxed.
>
> I'm aiming to merge this for v4.8 which should get this a fair few weeks in -next.
Thanks Peter, the arm/arm64 bits all look good to me.
Will
Powered by blists - more mailing lists