From owner-freebsd-arch@FreeBSD.ORG Sat Jun 28 00:46:12 2003 Return-Path: Delivered-To: freebsd-arch@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id F034637B401 for ; Sat, 28 Jun 2003 00:46:12 -0700 (PDT) Received: from heron.mail.pas.earthlink.net (heron.mail.pas.earthlink.net [207.217.120.189]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5956243FD7 for ; Sat, 28 Jun 2003 00:46:12 -0700 (PDT) (envelope-from tlambert2@mindspring.com) Received: from user-2ivfjii.dialup.mindspring.com ([165.247.206.82] helo=mindspring.com) by heron.mail.pas.earthlink.net with asmtp (SSLv3:RC4-MD5:128) (Exim 3.33 #1) id 19WAPS-0004dd-00; Sat, 28 Jun 2003 00:46:11 -0700 Message-ID: <3EFD4755.49BAF150@mindspring.com> Date: Sat, 28 Jun 2003 00:44:21 -0700 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: Andrew Gallatin References: <3EF3C12F.9060303@btc.adaptec.com> <16124.39930.142492.356163@grasshopper.cs.duke.edu> <3EFC9F2D.6020908@btc.adaptec.com> <16124.43999.333761.397624@grasshopper.cs.duke.edu> <16124.45051.919899.414795@grasshopper.cs.duke.edu> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-ELNK-Trace: b1a02af9316fbb217a47c185c03b154d40683398e744b8a4574c562441626f6360c4526e0ed31fa12601a10902912494350badd9bab72f9c350badd9bab72f9c cc: Scott Long cc: freebsd-arch@freebsd.org Subject: Re: API change for bus_dma X-BeenThere: freebsd-arch@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Discussion related to FreeBSD architecture List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 28 Jun 2003 07:46:13 -0000 Andrew Gallatin wrote: > Most sparc's have 2 different sorts of DMA modes. One is cache > coherent (aka DDI_DMA_CONSISTENT) -- this is what we all know and love > from PC, alphas, macs, etc. "contiguous" > The other mode (DDI_DMA_STREAMING) allows non cache coherent DMA. > This requires you to call ddi_dma_sync() between your last touch of > the data and you starting a DMA read from a device. And vice-versa > for a DMA write. "scatter/gather" > The reason people use DDI_DMA_STREAMING is because coherent DMA > bandwith tends to be abysmal on most sparcs. I'm not surprised; in order to present a contiguous physical RAM buffer to the device DMA engine, you have two choices: 1) Get lucky 2) Copy the data before triggering the DMA The data copy is what kills you. -- Terry