From mboxrd@z Thu Jan 1 00:00:00 1970 From: Roland Dreier Subject: Re: [openib-general] [PATCH v4 01/13] Linux RDMA Core Changes Date: Thu, 04 Jan 2007 13:34:27 -0800 Message-ID: References: <1167851839.4187.36.camel@stevo-desktop> <20070103193324.GD29003@mellanox.co.il> <1167855618.4187.65.camel@stevo-desktop> <1167859320.4187.81.camel@stevo-desktop> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: "Michael S. Tsirkin" , netdev@vger.kernel.org, linux-kernel@vger.kernel.org, openib-general@openib.org Return-path: To: Steve Wise In-Reply-To: <1167859320.4187.81.camel@stevo-desktop> (Steve Wise's message of "Wed, 03 Jan 2007 15:22:00 -0600") Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org OK, I'm back from vacation today. Anyway I don't have a definitive statement on this right now. I guess I agree that I don't like having an extra parameter to a function that should be pretty fast (although req notify isn't quite as hot as something like posting a send request or polling a cq), given that it adds measurable overhead. (And I am surprised that the overhead is measurable, since 3 arguments still fit in registers, but OK). I also agree that adding an extra entry point just to pass in the user data is ugly, and also racy. Giving the kernel driver a pointer it can read seems OK I guess, although it's a little ugly to have a backdoor channel like that. I'm somewhat surprised the driver has to go into the kernel to rearm a CQ -- what makes the operation need kernel privileges? (Sorry for not reading the code)