linux-kernel - RE: perf events ring buffer memory barrier on powerpc

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <OFF094B66E.899BE5FF-ON42257C15.0045F3A1-42257C15.0046FE15@il.ibm.com>
Date:	Thu, 31 Oct 2013 14:55:25 +0200
From:	Victor Kaplansky <VICTORK@...ibm.com>
To:	"David Laight" <David.Laight@...lab.com>
Cc:	"Anton Blanchard" <anton@...ba.org>,
	"Frederic Weisbecker" <fweisbec@...il.com>,
	"LKML" <linux-kernel@...r.kernel.org>,
	"Linux PPC dev" <linuxppc-dev@...abs.org>,
	"Mathieu Desnoyers" <mathieu.desnoyers@...ymtl.ca>,
	"Michael Neuling" <mikey@...ling.org>,
	"Oleg Nesterov" <oleg@...hat.com>, paulmck@...ux.vnet.ibm.com,
	"Peter Zijlstra" <peterz@...radead.org>
Subject: RE: perf events ring buffer memory barrier on powerpc

"David Laight" <David.Laight@...lab.com> wrote on 10/31/2013 02:28:56 PM:

> So even though the wmb() in the writer ensures the writes are correctly
> ordered, the reader can read the old value from the second location from
> its local cache.

In case of circular buffer, the only thing that producer reads is @tail,
and nothing wrong will happen if producer reads old value of @tail.
Moreover,
adherents of smp_mb() insert it *after* the read of @tail, so it cannot
prevent reading of old value anyway.
-- Victor

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/