netdev - Re: [PATCH v4 00/12] remove msize limit in virtio transport

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: <2799122.FyIdJ7nTd3@silver>
Date:   Tue, 24 May 2022 13:29:18 +0200
From:   Christian Schoenebeck <linux_oss@...debyte.com>
To:     Dominique Martinet <asmadeus@...ewreck.org>,
        Nikolay Kichukov <nikolay@...um.net>
Cc:     v9fs-developer@...ts.sourceforge.net, netdev@...r.kernel.org,
        Eric Van Hensbergen <ericvh@...il.com>,
        Latchesar Ionkov <lucho@...kov.net>,
        Greg Kurz <groug@...d.org>, Vivek Goyal <vgoyal@...hat.com>
Subject: Re: [PATCH v4 00/12] remove msize limit in virtio transport

On Dienstag, 24. Mai 2022 10:10:31 CEST Nikolay Kichukov wrote:
> Hello Dominique,
> 
> On Mon, 2022-01-24 at 20:07 +0900, Dominique Martinet wrote:
> > Nikolay Kichukov wrote on Mon, Jan 24, 2022 at 11:21:08AM +0100:
> > > It works, sorry for overlooking the 'known limitations' in the first
> > > place. When do we expect these patches to be merged upstream?
> > 
> > We're just starting a new development cycle for 5.18 while 5.17 is
> > stabilizing, so this mostly depends on the ability to check if a msize
> > given in parameter is valid as described in the first "STILL TO DO"
> > point listed in the cover letter.
> > 
> > I personally would be happy considering this series for this cycle
> > with
> > just a max msize of 4MB-8k and leave that further bump for later if
> > we're sure qemu will handle it.
> > We're still seeing a boost for that and the smaller buffers for small
> > messages will benefit all transport types, so that would get in in
> > roughly two months for 5.18-rc1, then another two months for 5.18 to
> > actually be released and start hitting production code.
> > 
> > 
> > I'm not sure when exactly but I'll run some tests with it as well and
> > redo a proper code review within the next few weeks, so we can get
> > this
> > in -next for a little while before the merge window.
> 
> Did you make it into 5.18? I see it just got released...

No, not yet. I can send a v5 as outlined above, including opt-out for the RDMA 
transport as Dominique noted, that wouldn't be much work for me.

However ATM I fear it would probably not help anybody, as we currently have 
two far more serious issues [1] regarding 9p's cache support introduced by the 
netfs changes: 

1. 9p cache enabled performs now worse than without any cache.

2. There are misbehaviours once in a while, as 9p cache opens FIDs in read-
only mode and once in a while then tries to write with those read-only FIDs 
which causes EBADF errors.

[1] https://lore.kernel.org/lkml/9591612.lsmsJCMaJN@silver/

Issue (2.) can probably be fixed by just opening the FIDs in RW mode, as 
suggested by Dominique. But for performance issue (1.) nobody had an idea yet.

Best regards,
Christian Schoenebeck