From: Will Deacon <will.deacon@arm.com>
To: Manfred Spraul <manfred@colorfullife.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
benh@kernel.crashing.org, paulmck@linux.vnet.ibm.com,
Ingo Molnar <mingo@elte.hu>, Boqun Feng <boqun.feng@gmail.com>,
Andrew Morton <akpm@linux-foundation.org>,
LKML <linux-kernel@vger.kernel.org>,
1vier1@web.de, Davidlohr Bueso <dave@stgolabs.net>
Subject: Re: [PATCH 1/4] spinlock: Document memory barrier rules
Date: Thu, 1 Sep 2016 12:19:15 +0100 [thread overview]
Message-ID: <20160901111915.GB6721@arm.com> (raw)
In-Reply-To: <3f7c39e5-4c46-0641-d29e-36c9439ad6dc@colorfullife.com>
On Thu, Sep 01, 2016 at 01:04:26PM +0200, Manfred Spraul wrote:
> If I understand it right, the rules are:
> 1. spin_unlock_wait() must behave like spin_lock();spin_unlock();
> 2. spin_is_locked() must behave like spin_trylock() ? spin_unlock(),TRUE :
> FALSE
I don't think spin_is_locked is as strong as all that. On arm64 and ppc,
it's just smp_mb(); followed by a check on the lock value. It can't be
used for the same sorts of inter-CPU synchronisation that spin_unlock_wait
provides.
> 3. the ACQUIRE during spin_lock applies to the lock load, not to the store.
Correct. This is already documented for things like cmpxchg.
> sem.c and nf_conntrack.c need only rule 1 now, but I would document the rest
> as well, ok?
>
> I'll update the patches.
Please CC me!
Will
next prev parent reply other threads:[~2016-09-01 11:19 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-08-28 11:56 [PATCH 0/4] Clarify/standardize memory barriers for lock/unlock Manfred Spraul
2016-08-28 11:56 ` [PATCH 1/4] spinlock: Document memory barrier rules Manfred Spraul
2016-08-28 11:56 ` [PATCH 2/4] barrier.h: Move smp_mb__after_unlock_lock to barrier.h Manfred Spraul
2016-08-28 11:56 ` [PATCH 3/4] net/netfilter/nf_conntrack_core: update memory barriers Manfred Spraul
2016-08-28 11:56 ` [PATCH 4/4] qspinlock for x86: smp_mb__after_spin_lock() is free Manfred Spraul
2016-08-29 10:52 ` Peter Zijlstra
2016-08-29 10:51 ` [PATCH 3/4] net/netfilter/nf_conntrack_core: update memory barriers Peter Zijlstra
2016-08-28 13:43 ` [PATCH 2/4] barrier.h: Move smp_mb__after_unlock_lock to barrier.h Paul E. McKenney
2016-08-28 16:31 ` Manfred Spraul
2016-08-28 18:00 ` Manfred Spraul
2016-08-28 14:41 ` kbuild test robot
2016-08-28 17:43 ` [PATCH 2/4 v3] spinlock.h: Move smp_mb__after_unlock_lock to spinlock.h Manfred Spraul
2016-08-29 10:48 ` [PATCH 1/4] spinlock: Document memory barrier rules Peter Zijlstra
2016-08-29 12:54 ` Manfred Spraul
2016-08-29 13:44 ` Peter Zijlstra
2016-08-31 4:59 ` Manfred Spraul
2016-08-31 15:40 ` Peter Zijlstra
2016-08-31 16:40 ` Will Deacon
2016-08-31 18:32 ` Manfred Spraul
2016-09-01 8:44 ` Peter Zijlstra
2016-09-01 11:04 ` Manfred Spraul
2016-09-01 11:19 ` Will Deacon [this message]
2016-09-01 11:51 ` Peter Zijlstra
2016-09-01 14:05 ` Boqun Feng
2016-08-29 10:53 ` [PATCH 0/4] Clarify/standardize memory barriers for lock/unlock Peter Zijlstra
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=20160901111915.GB6721@arm.com \
--to=will.deacon@arm.com \
--cc=1vier1@web.de \
--cc=akpm@linux-foundation.org \
--cc=benh@kernel.crashing.org \
--cc=boqun.feng@gmail.com \
--cc=dave@stgolabs.net \
--cc=linux-kernel@vger.kernel.org \
--cc=manfred@colorfullife.com \
--cc=mingo@elte.hu \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.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).