From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Gunthorpe Subject: Re: [PATCH 2/2] IB/mad: Use IDR for agent IDs Date: Sun, 10 Jun 2018 14:30:27 -0600 Message-ID: <20180610203027.GF5560@mellanox.com> References: <20180608174218.32455-1-willy@infradead.org> <20180608174218.32455-3-willy@infradead.org> <20180610063028.GH12407@mtr-leonro.mtl.com> <20180610104305.GA9284@bombadil.infradead.org> <20180610122505.GM12407@mtr-leonro.mtl.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20180610122505.GM12407@mtr-leonro.mtl.com> Sender: linux-kernel-owner@vger.kernel.org To: Leon Romanovsky Cc: Matthew Wilcox , hans.westgaard.ry@oracle.com, Doug Ledford , Matthew Wilcox , linux-rdma@vger.kernel.org, =?utf-8?B?SMOla29u?= Bugge , Parav Pandit , Jack Morgenstein , Pravin Shedge , linux-kernel@vger.kernel.org List-Id: linux-rdma@vger.kernel.org On Sun, Jun 10, 2018 at 03:25:05PM +0300, Leon Romanovsky wrote: > On Sun, Jun 10, 2018 at 03:43:05AM -0700, Matthew Wilcox wrote: > > On Sun, Jun 10, 2018 at 09:30:28AM +0300, Leon Romanovsky wrote: > > > 1. IBTA spec doesn't talk at all about the size of TransactionID, more > > > on that in section "13.4.6.4 TRANSACTION ID USAGE", the specification > > > says: "The contents of the TransactionID (TID) field are implementation- > > > dependent. So let's don't call it mlx4 bug. > > > > I was loosely paraphrasing the original bug report; suggested rewording > > of the comments gratefully accepted. > > Just replace "mlx4 bug" with something like "to comply with mlx4 > implementation". Well, it is a bug. Blindly replacing the upper 8 bits of the TID in a driver without accommodation from the core is totally, bonkers wrong. The original concept was that the 1<<24 limit would come from the driver and only mlx4 would have less than 1<<32, because only mlx4 does this thing.. Thanks Matt, Jason