From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Hellwig Subject: Re: Regression in 4.14: wrong data being read from bcache device Date: Fri, 17 Nov 2017 16:08:28 +0100 Message-ID: <20171117150828.GA24694@lst.de> References: <1321800569.20171116152838@pvgoran.name> <8a3d34b9-c49f-3870-fc7f-d337f7077c32@kernel.dk> <3474003b-b49f-d811-4116-e2d5fac730ce@lyle.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from verein.lst.de ([213.95.11.211]:49126 "EHLO newverein.lst.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S964890AbdKQPIa (ORCPT ); Fri, 17 Nov 2017 10:08:30 -0500 Content-Disposition: inline In-Reply-To: Sender: linux-bcache-owner@vger.kernel.org List-Id: linux-bcache@vger.kernel.org To: Michael Lyle Cc: Jens Axboe , Campbell Steven , Pavel Goran , linux-bcache , "linux-block@vger.kernel.org" , Kent Overstreet , hch@lst.de On Thu, Nov 16, 2017 at 07:07:40PM -0800, Michael Lyle wrote: > I think the probable cause is this: we construct bios based on > previously completed bios in a few places, That is an extremely bad idea in many ways, so I think we'll need to fix this as the priority.