linux-kernel - Re: [PATCH 8/8] fs/aio: Use rcu_work instead of explicit rcu and work item

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: <20180321164000.GC2149215@devbig577.frc2.facebook.com>
Date:   Wed, 21 Mar 2018 09:40:00 -0700
From:   Tejun Heo <tj@...nel.org>
To:     Oleg Nesterov <oleg@...hat.com>
Cc:     torvalds@...ux-foundation.org, jannh@...gle.com,
        paulmck@...ux.vnet.ibm.com, bcrl@...ck.org,
        viro@...iv.linux.org.uk, kent.overstreet@...il.com,
        security@...nel.org, linux-kernel@...r.kernel.org,
        kernel-team@...com
Subject: Re: [PATCH 8/8] fs/aio: Use rcu_work instead of explicit rcu and
 work item

Hey, Oleg.

On Wed, Mar 21, 2018 at 04:58:13PM +0100, Oleg Nesterov wrote:
> > -	struct rcu_head		free_rcu;
> > -	struct work_struct	free_work;	/* see free_ioctx() */
> > +	struct rcu_work		free_rwork;	/* see free_ioctx() */
> 
> IIUC, you can't easily share rcu_work's, thus every kioctx needs its own
> ->free_rwork and this looks sub-optimal.
>
> What do you think about the (untested) patch below?
> 
> Oleg.
> 
> 
> --- a/fs/aio.c
> +++ b/fs/aio.c
> @@ -115,8 +115,10 @@ struct kioctx {
>  	struct page		**ring_pages;
>  	long			nr_pages;
>  
> -	struct rcu_head		free_rcu;
> -	struct work_struct	free_work;	/* see free_ioctx() */
> +	union {
> +		struct rcu_head		free_rcu;
> +		struct llist_node	free_llist;
> +	};

It really depends on how much we want to optimize.  Do you think it
matters enough?

Thanks.

-- 
tejun