From owner-svn-src-all@freebsd.org Wed Jul 13 16:19:46 2016 Return-Path: Delivered-To: svn-src-all@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 54E80B98BB3; Wed, 13 Jul 2016 16:19:46 +0000 (UTC) (envelope-from ae@FreeBSD.org) Received: from mx2.freebsd.org (mx2.freebsd.org [8.8.178.116]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "mx2.freebsd.org", Issuer "Gandi Standard SSL CA 2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 3932E1973; Wed, 13 Jul 2016 16:19:46 +0000 (UTC) (envelope-from ae@FreeBSD.org) Received: from butcher-nb.yandex.net (freefall.freebsd.org [IPv6:2001:1900:2254:206c::16:87]) by mx2.freebsd.org (Postfix) with ESMTP id 58544448C; Wed, 13 Jul 2016 16:19:44 +0000 (UTC) (envelope-from ae@FreeBSD.org) Subject: Re: svn commit: r271300 - in head/sys: net netinet To: Adrian Chadd , src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org References: <201409090418.s894IKMT007235@svn.freebsd.org> From: "Andrey V. Elsukov" Message-ID: <578669BC.1010202@FreeBSD.org> Date: Wed, 13 Jul 2016 19:18:04 +0300 User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:38.0) Gecko/20100101 Thunderbird/38.7.1 MIME-Version: 1.0 In-Reply-To: <201409090418.s894IKMT007235@svn.freebsd.org> Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="N7uKfB0JtiLALv56aRAraPdfHpTI6VOPd" X-BeenThere: svn-src-all@freebsd.org X-Mailman-Version: 2.1.22 Precedence: list List-Id: "SVN commit messages for the entire src tree \(except for " user" and " projects" \)" List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 13 Jul 2016 16:19:46 -0000 This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --N7uKfB0JtiLALv56aRAraPdfHpTI6VOPd Content-Type: multipart/mixed; boundary="4g5PdQ05NSDW09jb8KJ2QvHrVwrFKgCOv" From: "Andrey V. Elsukov" To: Adrian Chadd , src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org Message-ID: <578669BC.1010202@FreeBSD.org> Subject: Re: svn commit: r271300 - in head/sys: net netinet References: <201409090418.s894IKMT007235@svn.freebsd.org> In-Reply-To: <201409090418.s894IKMT007235@svn.freebsd.org> --4g5PdQ05NSDW09jb8KJ2QvHrVwrFKgCOv Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable On 09.09.14 08:18, Adrian Chadd wrote: > Author: adrian > Date: Tue Sep 9 04:18:20 2014 > New Revision: 271300 > URL: http://svnweb.freebsd.org/changeset/base/271300 >=20 > Log: > Update the IPv4 input path to handle reassembled frames and incoming = frames > with no RSS hash. > =20 > When doing RSS: > =20 > * Create a new IPv4 netisr which expects the frames to have been veri= fied; > it just directly dispatches to the IPv4 input path. > * Once IPv4 reassembly is done, re-calculate the RSS hash with the ne= w > IP and L3 header; then reinject it as appropriate. > * Update the IPv4 netisr to be a CPU affinity netisr with the RSS has= h > function (rss_soft_m2cpuid) - this will do a software hash if the > hardware doesn't provide one. > =20 > NICs that don't implement hardware RSS hashing will now benefit from = RSS > distribution - it'll inject into the correct destination netisr. > =20 > Note: the netisr distribution doesn't work out of the box - netisr do= esn't > query RSS for how many CPUs and the affinity setup. Yes, netisr like= ly > shouldn't really be doing CPU stuff anymore and should be "some kind = of > 'thing' that is a workqueue that may or may not have any CPU affinity= "; > that's for a later commit. > =20 > Differential Revision: https://reviews.freebsd.org/D527 > Reviewed by: grehan >=20 > Modified: > head/sys/net/netisr.h > head/sys/netinet/in_var.h > head/sys/netinet/ip_input.c >=20 > Modified: head/sys/netinet/ip_input.c Hi, I am sorry for addressing this old message, but it looks like you can not use the same IPCTL_XXX constant for several different oids. =2E.. > @@ -266,6 +292,46 @@ SYSCTL_PROC(_net_inet_ip, IPCTL_INTRQDRO ^^^^ - there > CTLTYPE_INT|CTLFLAG_RD, 0, 0, sysctl_netinet_intr_queue_drops, "I"= , > "Number of packets dropped from the IP input queue"); > =20 > +SYSCTL_PROC(_net_inet_ip, IPCTL_INTRQMAXLEN, intr_direct_queue_maxlen,= ^^^ - and there. > + CTLTYPE_INT|CTLFLAG_RW, 0, 0, sysctl_netinet_intr_direct_queue_max= len, "I", > + "Maximum size of the IP direct input queue"); User applications use these constants to address specific oids and I don't think and don't see that the kernel calls several handlers for one oid. --=20 WBR, Andrey V. Elsukov --4g5PdQ05NSDW09jb8KJ2QvHrVwrFKgCOv-- --N7uKfB0JtiLALv56aRAraPdfHpTI6VOPd Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/ iQEcBAEBCAAGBQJXhmm9AAoJEAHF6gQQyKF6Gu8H/2pD3KygH9ApWnN+5K/a1ZRh o3dFQh8ds0eQ5+bAbNB7+62sO54RQHWZlF15KDoGJOmXg8QBy66nhxF/gdeQxkYa 7dnH2hK4A5E9TsEvWY/7BJXBpHWX5MVSb+klSps3cO66MZ74qsxn42HtYcyhsVzK wmvDKFelQI1cJLnP2VOT/VJtxsisWeeFDiOTLj46Que2NqKUJJ+VSs5umjx/ayQV nMcglh/UrnbwHwgQE89jcAnPk92GX4cPaP+rKQBU/TUZoZUJCgUzTBQjuxCm/MQs CzdE3DOgYDH8C7K5strS9ttGowg6raMcx9RdlCkeYsRr/WC4OlL7pHBYzodUVqo= =NIRd -----END PGP SIGNATURE----- --N7uKfB0JtiLALv56aRAraPdfHpTI6VOPd--