linux-kernel - Re: [PATCH] padata: use smp_mb in padata_reorder to avoid orphaned padata jobs

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: <20190712100636.mqdr567p7ozanlyl@gondor.apana.org.au>
Date:   Fri, 12 Jul 2019 18:06:36 +0800
From:   Herbert Xu <herbert@...dor.apana.org.au>
To:     Daniel Jordan <daniel.m.jordan@...cle.com>
Cc:     steffen.klassert@...unet.com, daniel.m.jordan@...cle.com,
        andrea.parri@...rulasolutions.com, boqun.feng@...il.com,
        paulmck@...ux.ibm.com, peterz@...radead.org,
        linux-arch@...r.kernel.org, linux-crypto@...r.kernel.org,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH] padata: use smp_mb in padata_reorder to avoid orphaned
 padata jobs

Daniel Jordan <daniel.m.jordan@...cle.com> wrote:
>
> CPU0                                 CPU1
> 
> padata_reorder                       padata_do_serial
>  LOAD reorder_objects  // 0
>                                       INC reorder_objects  // 1
>                                       padata_reorder
>                                         TRYLOCK pd->lock   // failed
>  UNLOCK pd->lock

I think this can't happen because CPU1 won't call padata_reorder
at all as it's the wrong CPU so it gets pushed back onto a work
queue which will go back to CPU0.

Steffen, could you please take a look at this as there clearly
is a problem here?

Thanks,
-- 
Email: Herbert Xu <herbert@...dor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt