From mboxrd@z Thu Jan 1 00:00:00 1970 From: Leon Romanovsky Subject: Re: [RFC ABI 0/8] Netlink-based IOCTLs RDMA ABI Date: Tue, 31 May 2016 21:10:12 +0300 Message-ID: <20160531181012.GD7477@leon.nu> References: <20160524223052.GI7950@obsidianresearch.com> <20160526172244.GC27115@obsidianresearch.com> <1828884A29C6694DAF28B7E6B8A82373AB05BB5D@ORSMSX109.amr.corp.intel.com> <20160526233612.GA4396@obsidianresearch.com> <1828884A29C6694DAF28B7E6B8A82373AB05BC0C@ORSMSX109.amr.corp.intel.com> <20160527131956.GY25500@leon.nu> <1828884A29C6694DAF28B7E6B8A82373AB05BD12@ORSMSX109.amr.corp.intel.com> <20160529081646.GA25500@leon.nu> <1828884A29C6694DAF28B7E6B8A82373AB05CA92@ORSMSX109.amr.corp.intel.com> Reply-To: leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="cHMo6Wbp1wrKhbfi" Return-path: Content-Disposition: inline In-Reply-To: <1828884A29C6694DAF28B7E6B8A82373AB05CA92-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: "Hefty, Sean" Cc: Jason Gunthorpe , Matan Barak , "dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org" , "linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" List-Id: linux-rdma@vger.kernel.org --cHMo6Wbp1wrKhbfi Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Tue, May 31, 2016 at 05:56:29PM +0000, Hefty, Sean wrote: > > > I am referring to the creation of an ioctl handling framework that is= suitable for use by the rdma > > cm, ib cm (if kept), verb devices, and non-verbs drivers that do not pl= ug into the kernel verbs > > framework. The kernel clients are the items I mentioned. Having a com= mon ioctl handling framework > > will maximize code reuse. > >=20 > > It looks too generic for RDMA subsystem. What does it make this IOCTL f= ramework specific to RDMA? >=20 > I'm not sure how something can be too generic. Everything I mentioned ab= ove exists as part of the RDMA subsystem. If I understand your proposal correctly, the proposed IOCTL framework will = be able to handle all types of objects without any limitations in order and lo= cking, everything is going to be processed by the driver, which will decide if such object/method is supported or not. What will stop the GPU with DRMs to use it? --cHMo6Wbp1wrKhbfi Content-Type: application/pgp-signature; name="signature.asc" Content-Description: Digital signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIbBAEBAgAGBQJXTdODAAoJEORje4g2clinqaMP+J/rWskV3Y/m4//aeP+B5PFX VHgneNzR0cb6qywcbskCvaJ3sjM5S6EAG0gjjaQKxPz/TO3r35MIeHSfGpvCXyld SSHNc//JzIF7YlCfINrP8AGoQvj78HrBBvsYmMYcs5bKL1z9/cmW3+xXJJUYc0Jh kNx4/JF0MW17PPKtxSFTmHmns4sHwWLoiwWgztKsuLqXeEmeIax3vKPB/I78INHJ BqgGH4JVuuTfk2aqD5RmH619HfgTI4HkkeObV8P63UmV2KfJt77a7OqNCEpsCXXQ zJmLELISamnsw5ekH/yK5/ECpnPN8J3U0hx7puYER4YC+tyW+z/kGHxpQOiw9sFs Citv8NRhrjA6lNyQgpM4Q2luBanUzz1a4rVVowccOC9NKzb6HDxRaFyYrC49zwJq 3NdnQ3o0HH9RZl4OpVgqKbOiWw3Id0yUJyZfatXbugeETIWQf8VoEy1CPN+RwiuD 6QiO55M7OYASl0wQeGTC/xou89sikgSy2LTBt6g9+aWq7pDAeZotKb9k8nVv9CA/ lIOn55q2lpHMfEFUg69kZL0+rVZp+xl6D/IZSf43QTMj1Pg7KwlgbY8TNFrV9Nqz Mu/gscpIYphgFDIUDjAhRHxNjmR7hCgexRQAwm/t1MEvoTrGexb7H9LqFjECj+jc XY16oti0xf0tbfbX7E8= =k40M -----END PGP SIGNATURE----- --cHMo6Wbp1wrKhbfi-- -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html