From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761213Ab2DKXGV (ORCPT ); Wed, 11 Apr 2012 19:06:21 -0400 Received: from caramon.arm.linux.org.uk ([78.32.30.218]:52734 "EHLO caramon.arm.linux.org.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751537Ab2DKXGU (ORCPT ); Wed, 11 Apr 2012 19:06:20 -0400 Date: Thu, 12 Apr 2012 00:05:58 +0100 From: Russell King - ARM Linux To: Linus Walleij Cc: Vinod Koul , linux-kernel@vger.kernel.org, Dan Williams , linux-arm-kernel@lists.infradead.org, Viresh Kumar , Alim Akhtar , Alessandro Rubini Subject: Re: [PATCH 2/2 v2] dma/amba-pl08x: add support for the Nomadik variant Message-ID: <20120411230558.GF24211@n2100.arm.linux.org.uk> References: <1334185214-27250-1-git-send-email-linus.walleij@linaro.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1334185214-27250-1-git-send-email-linus.walleij@linaro.org> User-Agent: Mutt/1.5.19 (2009-01-05) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Apr 12, 2012 at 01:00:14AM +0200, Linus Walleij wrote: > The Nomadik PL080 variant has some extra protection bits that > may be set, so we need to check these bits to see if the > channels are actually available for the DMAengine to use. Actually, there is another issue to be considered with PL080. For memcpy transfers, a restricted set of channels should be used, because the PL080 only guarantees certain channels won't consume all bus bandwidth, locking out (eg) the CPU from doing other stuff while the memcpy DMA is running. So really the way physical channels are selected needs to become more inteligent overall. From mboxrd@z Thu Jan 1 00:00:00 1970 From: linux@arm.linux.org.uk (Russell King - ARM Linux) Date: Thu, 12 Apr 2012 00:05:58 +0100 Subject: [PATCH 2/2 v2] dma/amba-pl08x: add support for the Nomadik variant In-Reply-To: <1334185214-27250-1-git-send-email-linus.walleij@linaro.org> References: <1334185214-27250-1-git-send-email-linus.walleij@linaro.org> Message-ID: <20120411230558.GF24211@n2100.arm.linux.org.uk> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Thu, Apr 12, 2012 at 01:00:14AM +0200, Linus Walleij wrote: > The Nomadik PL080 variant has some extra protection bits that > may be set, so we need to check these bits to see if the > channels are actually available for the DMAengine to use. Actually, there is another issue to be considered with PL080. For memcpy transfers, a restricted set of channels should be used, because the PL080 only guarantees certain channels won't consume all bus bandwidth, locking out (eg) the CPU from doing other stuff while the memcpy DMA is running. So really the way physical channels are selected needs to become more inteligent overall.