From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ale.deltatee.com (ale.deltatee.com. [207.54.116.67]) by gmr-mx.google.com with ESMTPS id z1si65640pfh.0.2017.12.05.11.46.08 for (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Tue, 05 Dec 2017 11:46:09 -0800 (PST) References: <20171204175721.10322-1-logang@deltatee.com> From: Logan Gunthorpe Message-ID: Date: Tue, 5 Dec 2017 12:46:06 -0700 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 7bit Subject: Re: [PATCH v2] ntb_hw_switchtec: Force down the link before initializing To: Jon Mason Cc: linux-ntb , ThanhTuThai List-ID: On 05/12/17 12:30 PM, Jon Mason wrote: > On Mon, Dec 4, 2017 at 12:57 PM, Logan Gunthorpe wrote: >> If one host crashes and soft reboots, the other host may not see a >> link down event. Then when the crashed host comes back up, the >> surviving host may not know the link was reset and the NTB clients >> may not work without being reset. >> >> To solve this, we send a LINK_FORCE_DOWN message to each peer every >> time we come up, before we register the NTB device. If a surviving >> host still thinks the link is up it will take it down immediately. >> In this way, once the crashed host comes up fully, it will send a >> regular link up event as per usual and the link will be properly >> restarted. >> >> While we are in the area, this also fixes the MSG_LINK_UP message that >> was in the link down function that was reported by Doug Meyers. > > So, this only applies on the ntb-next branch, and applying it after > your multi-partition patch series causes it to fail to apply. The > fixup appears to be trivial, but please double check me. Oops sorry. I think I checked that v1 merged cleanly but didn't look at v2. I double checked the merged commit in ntb-next and it looks good. I'll do some testing on ntb-next later in the week. Thanks, Logan