[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20171226205436.GA32546@splinter>
Date: Tue, 26 Dec 2017 22:54:37 +0200
From: Ido Schimmel <idosch@...sch.org>
To: Willy Tarreau <w@....eu>
Cc: Wei Wang <weiwan@...gle.com>, Martin KaFai Lau <kafai@...com>,
Eric Dumazet <edumazet@...gle.com>,
"David S. Miller" <davem@...emloft.net>,
Sasha Levin <alexander.levin@...izon.com>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Chris Rankin <rankincj@...il.com>,
linux-kernel@...r.kernel.org, stable@...r.kernel.org,
netdev@...r.kernel.org
Subject: Re: BUG warnings in 4.14.9
On Tue, Dec 26, 2017 at 07:59:55PM +0100, Willy Tarreau wrote:
> Guys,
>
> Chris reported the bug below and confirmed that reverting commit
> 9704f81 (ipv6: grab rt->rt6i_ref before allocating pcpu rt) seems to
> have fixed the issue for him. This patch is a94b9367 in mainline.
>
> I personally have no opinion on the patch, just found it because it
> was the only one touching this area between 4.14.8 and 4.14.9 :-)
>
> Should this be reverted or maybe fixed differently ?
Maybe I'm missing something, but how come this patch even made its way
into 4.14.y? It's part of a series to RCU-ify IPv6 FIB lookup that went
into 4.15.
Anyway, the mentioned bug was already fixed by commit 951f788a80ff
("ipv6: fix a BUG in rt6_get_pcpu_route()") when the code was still in
net-next.
Powered by blists - more mailing lists