From owner-cvs-src-old@FreeBSD.ORG Fri Jun 11 03:00:56 2010 Return-Path: Delivered-To: cvs-src-old@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 55C9F10656C6 for ; Fri, 11 Jun 2010 03:00:56 +0000 (UTC) (envelope-from marcel@FreeBSD.org) Received: from repoman.freebsd.org (unknown [IPv6:2001:4f8:fff6::29]) by mx1.freebsd.org (Postfix) with ESMTP id 439308FC1A for ; Fri, 11 Jun 2010 03:00:56 +0000 (UTC) Received: from repoman.freebsd.org (localhost [127.0.0.1]) by repoman.freebsd.org (8.14.3/8.14.3) with ESMTP id o5B30uB3021828 for ; Fri, 11 Jun 2010 03:00:56 GMT (envelope-from marcel@repoman.freebsd.org) Received: (from svn2cvs@localhost) by repoman.freebsd.org (8.14.3/8.14.3/Submit) id o5B30u6N021827 for cvs-src-old@freebsd.org; Fri, 11 Jun 2010 03:00:56 GMT (envelope-from marcel@repoman.freebsd.org) Message-Id: <201006110300.o5B30u6N021827@repoman.freebsd.org> X-Authentication-Warning: repoman.freebsd.org: svn2cvs set sender to marcel@repoman.freebsd.org using -f From: Marcel Moolenaar Date: Fri, 11 Jun 2010 03:00:32 +0000 (UTC) To: cvs-src-old@freebsd.org X-FreeBSD-CVS-Branch: HEAD Subject: cvs commit: src/sys/ia64/ia64 busdma_machdep.c vm_machdep.c src/sys/ia64/include md_var.h X-BeenThere: cvs-src-old@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: **OBSOLETE** CVS commit messages for the src tree List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Jun 2010 03:00:56 -0000 marcel 2010-06-11 03:00:32 UTC FreeBSD src repository Modified files: sys/ia64/ia64 busdma_machdep.c vm_machdep.c sys/ia64/include md_var.h Log: SVN rev 209026 on 2010-06-11 03:00:32Z by marcel Bump MAX_BPAGES from 256 to 1024. It seems that a few drivers, bge(4) in particular, do not handle deferred DMA map load operations at all. Any error, and especially EINPROGRESS, is treated as a hard error and typically abort the current operation. The fact that the busdma code queues the load operation for when resources (i.e. bounce buffers in this particular case) are available makes this especially problematic. Bounce buffering, unlike what the PR synopsis would suggest, works fine. While on the subject, properly implement swi_vm(). PR: 147502 MFC after: 1 week Revision Changes Path 1.51 +2 -2 src/sys/ia64/ia64/busdma_machdep.c 1.100 +2 -3 src/sys/ia64/ia64/vm_machdep.c 1.33 +1 -0 src/sys/ia64/include/md_var.h