From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Hellwig Subject: Re: [PREEMPT-RT] [REPOST PATCH 1/5] scsi: bnx2i: convert to kworker Date: Mon, 7 Nov 2016 17:48:46 +0100 Message-ID: <20161107164846.GA1966@lst.de> References: <20160817101003.30055-1-bigeasy@linutronix.de> <20161107161901.GA12297@infradead.org> <20161107163848.GA1421@lst.de> <20161107164628.jrft3ovlp5myfvs5@linutronix.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from verein.lst.de ([213.95.11.211]:58008 "EHLO newverein.lst.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752174AbcKGQsr (ORCPT ); Mon, 7 Nov 2016 11:48:47 -0500 Content-Disposition: inline In-Reply-To: <20161107164628.jrft3ovlp5myfvs5@linutronix.de> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: Sebastian Andrzej Siewior Cc: Christoph Hellwig , Thomas Gleixner , Christoph Hellwig , "James E.J. Bottomley" , "Martin K. Petersen" , linux-scsi@vger.kernel.org, Chad Dupuis , rt@linutronix.de, QLogic-Storage-Upstream@qlogic.com, Johannes Thumshirn On Mon, Nov 07, 2016 at 05:46:29PM +0100, Sebastian Andrzej Siewior wrote: > sorry for the confusion in the subject. If I remember correctly you said > that we may not have enough room for a larger / work_struct struct and I > should keep the list for now. But that was for libfc where it only has a tiny bit of private data i nthe skb - this is for cnix which has plenty of space, and in fact probably should do the workqueue offload in the core before invoking the protocol drivers.