From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Gunthorpe Subject: Re: [PATCH 1/6] mm: make mm->pinned_vm an atomic64 counter Date: Wed, 23 Jan 2019 11:33:53 -0700 Message-ID: <20190123183353.GA15768@ziepe.ca> References: <20190121174220.10583-1-dave@stgolabs.net> <20190121174220.10583-2-dave@stgolabs.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20190121174220.10583-2-dave@stgolabs.net> Sender: linux-kernel-owner@vger.kernel.org To: Davidlohr Bueso Cc: akpm@linux-foundation.org, dledford@redhat.com, jack@suse.de, ira.weiny@intel.com, linux-rdma@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Davidlohr Bueso , Christoph Lameter , Jan Kara , Daniel Jordan List-Id: linux-rdma@vger.kernel.org On Mon, Jan 21, 2019 at 09:42:15AM -0800, Davidlohr Bueso wrote: > Taking a sleeping lock to _only_ increment a variable is quite the > overkill, and pretty much all users do this. Furthermore, some drivers > (ie: infiniband and scif) that need pinned semantics can go to quite > some trouble to actually delay via workqueue (un)accounting for pinned > pages when not possible to acquire it. > > By making the counter atomic we no longer need to hold the mmap_sem > and can simply some code around it for pinned_vm users. The counter > is 64-bit such that we need not worry about overflows such as rdma > user input controlled from userspace. I see a number of MM people Reviewed-by this so are we good to take this in the RDMA tree now? Regards, Jason