From mboxrd@z Thu Jan  1 00:00:00 1970
From: Al Viro <viro@ZenIV.linux.org.uk>
Subject: Re: dcache shrink list corruption?
Date: Tue, 29 Apr 2014 18:56:54 +0100
Message-ID: <20140429175654.GI18016@ZenIV.linux.org.uk>
References: <20140429160139.GA3113@tucsk.piliscsaba.szeredi.hu>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org
To: Miklos Szeredi <miklos@szeredi.hu>
Return-path: <linux-kernel-owner@vger.kernel.org>
Content-Disposition: inline
In-Reply-To: <20140429160139.GA3113@tucsk.piliscsaba.szeredi.hu>
Sender: linux-kernel-owner@vger.kernel.org
List-Id: linux-fsdevel.vger.kernel.org

On Tue, Apr 29, 2014 at 06:01:39PM +0200, Miklos Szeredi wrote:

> Attached patch is just a starting point (untested).  Not sure how to minimize
> contention without adding too much complexity.

Contention isn't the worst problem here - I'd expect the cacheline ping-pong
to hurt more...  I agree with the analysis, but I'd really like to avoid that
spinlock ;-/

Let me see if we can avoid that...  Oh, well - at least that's a good excuse
to take a break from fucking deadlock analysis around the damn acct(2), most
of VFS and network filesystems ;-/