From owner-cvs-all@FreeBSD.ORG Fri Nov 14 18:01:53 2003 Return-Path: Delivered-To: cvs-all@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id F10D116A4CE; Fri, 14 Nov 2003 18:01:53 -0800 (PST) Received: from harmony.village.org (rover.bsdimp.com [204.144.255.66]) by mx1.FreeBSD.org (Postfix) with ESMTP id D7BB343F93; Fri, 14 Nov 2003 18:01:52 -0800 (PST) (envelope-from imp@bsdimp.com) Received: from localhost (warner@rover2.village.org [10.0.0.1]) by harmony.village.org (8.12.9p2/8.12.9) with ESMTP id hAF21qeG002308; Fri, 14 Nov 2003 19:01:52 -0700 (MST) (envelope-from imp@bsdimp.com) Date: Fri, 14 Nov 2003 19:01:29 -0700 (MST) Message-Id: <20031114.190129.61829458.imp@bsdimp.com> To: rizzo@icir.org From: "M. Warner Losh" In-Reply-To: <20031114132714.A88606@xorpc.icir.org> References: <200311141900.hAEJ0XBn058450@repoman.freebsd.org> <20031114132714.A88606@xorpc.icir.org> X-Mailer: Mew version 2.1 on Emacs 21.3 / Mule 5.0 (SAKAKI) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit cc: cvs-src@FreeBSD.org cc: sam@FreeBSD.org cc: cvs-all@FreeBSD.org cc: src-committers@FreeBSD.org Subject: Re: cvs commit: src/sys/dev/an if_an.c if_anreg.h src/sys/dev/bfe if_bfe.c src/sys/dev/my if_my.c src/sys/dev/owi if_owi.c if_wivar.h src/sys/dev/re if_re.c src/sys/dev/wl if_wl.c src/sys/pci if_dc.c if_dcreg.h if_pcn.c if_pcnreg.h if_rl.c ... X-BeenThere: cvs-all@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: CVS commit messages for the entire tree List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 15 Nov 2003 02:01:54 -0000 In message: <20031114132714.A88606@xorpc.icir.org> Luigi Rizzo writes: : On Fri, Nov 14, 2003 at 11:00:33AM -0800, Sam Leffler wrote: : > sam 2003/11/14 11:00:33 PST : ... : > Log: : > Drop the driver lock around calls to if_input to avoid a LOR when : > the packets are immediately returned for sending (e.g. when bridging : > or packet forwarding). There are more efficient ways to do this : > but for now use the least intrusive approach. : : the number of places that this commit had to touch makes me : wonder whether it wouldn't be better to include somehow : these calls into the if_input routine somehow... That would be hard w/o passing the lock into the if_input routine, or putting the lock in ifnet. Warner