From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Hellwig Subject: Re: [PATCH 12/15] scsi: initial blk-mq support Date: Fri, 7 Feb 2014 04:51:47 -0800 Message-ID: <20140207125147.GA3198@infradead.org> References: <20140205124118.332902571@bombadil.infradead.org> <20140205124154.337539740@bombadil.infradead.org> <1391724663.14985.11.camel@haakon3.risingtidesystems.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from bombadil.infradead.org ([198.137.202.9]:33620 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753187AbaBGMvt (ORCPT ); Fri, 7 Feb 2014 07:51:49 -0500 Content-Disposition: inline In-Reply-To: <1391724663.14985.11.camel@haakon3.risingtidesystems.com> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: "Nicholas A. Bellinger" Cc: Christoph Hellwig , Jens Axboe , James Bottomley , linux-scsi@vger.kernel.org > Is there extra scsi_mq_done() part that does IPI here even necessary > anymore..? > > I was under the assumption that blk_mq_end_io() is already taking care > of this..? blk_mq_end_io does it, but given that the SCSI-specific I/O completion path is non-trivial I'd rather run it on the indicated CPU as well, similar to how the old blk-softirq code works. I'll send out a patch series that should make this area a lot cleaner and avoid having to implement the IPIs in each driver that wants or needs it soon. > OK, so your in-lining the allocation of data + protection SGLs from > blk-mq.. > > The original prototype code was doing these allocations separately below > for each pre-allocated cmd, and offering LLD's to optionally > pre-allocate their own descripts using sh->hostt->cmd_size if > necessary.. > > This was necessary to eliminate all fast-path allocations for > virtio-scsi, and I'd like to see something similar here as an optional > feature as well. It's present. The cmd_size host_template parameter is added in the previous series, and we still take it into account.