[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20221209212730.GA10554@pc-4.home>
Date: Fri, 9 Dec 2022 22:27:30 +0100
From: Guillaume Nault <gnault@...hat.com>
To: Benjamin Coddington <bcodding@...hat.com>
Cc: "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Philipp Reisner <philipp.reisner@...bit.com>,
Lars Ellenberg <lars.ellenberg@...bit.com>,
Christoph Böhmwalder
<christoph.boehmwalder@...bit.com>, Jens Axboe <axboe@...nel.dk>,
Josef Bacik <josef@...icpanda.com>,
Keith Busch <kbusch@...nel.org>,
Christoph Hellwig <hch@....de>,
Sagi Grimberg <sagi@...mberg.me>,
Lee Duncan <lduncan@...e.com>, Chris Leech <cleech@...hat.com>,
Mike Christie <michael.christie@...cle.com>,
"James E.J. Bottomley" <jejb@...ux.ibm.com>,
"Martin K. Petersen" <martin.petersen@...cle.com>,
Valentina Manea <valentina.manea.m@...il.com>,
Shuah Khan <shuah@...nel.org>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
David Howells <dhowells@...hat.com>,
Marc Dionne <marc.dionne@...istor.com>,
Steve French <sfrench@...ba.org>,
Christine Caulfield <ccaulfie@...hat.com>,
David Teigland <teigland@...hat.com>,
Mark Fasheh <mark@...heh.com>,
Joel Becker <jlbec@...lplan.org>,
Joseph Qi <joseph.qi@...ux.alibaba.com>,
Eric Van Hensbergen <ericvh@...il.com>,
Latchesar Ionkov <lucho@...kov.net>,
Dominique Martinet <asmadeus@...ewreck.org>,
Ilya Dryomov <idryomov@...il.com>,
Xiubo Li <xiubli@...hat.com>,
Chuck Lever <chuck.lever@...cle.com>,
Jeff Layton <jlayton@...nel.org>,
Trond Myklebust <trond.myklebust@...merspace.com>,
Anna Schumaker <anna@...nel.org>,
Steffen Klassert <steffen.klassert@...unet.com>,
Herbert Xu <herbert@...dor.apana.org.au>,
netdev@...r.kernel.org
Subject: Re: [PATCH net v2 2/3] Treewide: Stop corrupting socket's task_frag
On Fri, Dec 09, 2022 at 01:19:24PM -0500, Benjamin Coddington wrote:
> Since moving to memalloc_nofs_save/restore, SUNRPC has stopped setting the
> GFP_NOIO flag on sk_allocation which the networking system uses to decide
> when it is safe to use current->task_frag. The results of this are
> unexpected corruption in task_frag when SUNRPC is involved in memory
> reclaim.
>
> The corruption can be seen in crashes, but the root cause is often
> difficult to ascertain as a crashing machine's stack trace will have no
> evidence of being near NFS or SUNRPC code. I believe this problem to
> be much more pervasive than reports to the community may indicate.
>
> Fix this by having kernel users of sockets that may corrupt task_frag due
> to reclaim set sk_use_task_frag = false. Preemptively correcting this
> situation for users that still set sk_allocation allows them to convert to
> memalloc_nofs_save/restore without the same unexpected corruptions that are
> sure to follow, unlikely to show up in testing, and difficult to bisect.
Reviewed-by: Guillaume Nault <gnault@...hat.com>
Powered by blists - more mailing lists