[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200214163758.455gqh73dhzvbvtv@ca-dmjordan1.us.oracle.com>
Date: Fri, 14 Feb 2020 11:37:58 -0500
From: Daniel Jordan <daniel.m.jordan@...cle.com>
To: Yang Yingliang <yangyingliang@...wei.com>
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
linux-kernel@...r.kernel.org, stable@...r.kernel.org,
Herbert Xu <herbert@...dor.apana.org.au>,
Daniel Jordan <daniel.m.jordan@...cle.com>,
Sasha Levin <sashal@...nel.org>,
Steffen Klassert <steffen.klassert@...unet.com>
Subject: Re: [PATCH 4.19 091/195] padata: Remove broken queue flushing
Hello Yang,
On Fri, Feb 14, 2020 at 06:21:47PM +0800, Yang Yingliang wrote:
> On 2020/2/10 20:32, Greg Kroah-Hartman wrote:
> > @@ -501,8 +509,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
> > timer_setup(&pd->timer, padata_reorder_timer, 0);
> > atomic_set(&pd->seq_nr, -1);
> > atomic_set(&pd->reorder_objects, 0);
> > - atomic_set(&pd->refcnt, 0);
> > - pd->pinst = pinst;
> This patch remove this assignment, it's cause a null-ptr-deref when using
> pd->pinst in padata_reorder().
Thanks for reporting. This change is based on an enhancement in mainline that
moved this assignment but isn't in 4.19:
bfde23ce200e ("padata: unbind parallel jobs from specific CPUs")
A version of _this_ patch (i.e. remove broken queue flushing) has been posted
for 4.14, 4.9, and 4.4, all of which would likely result in the same issue, so
let's hold off on merging those until I can post fixed versions.
I'll start working on the 4.19 fix now.
Powered by blists - more mailing lists