From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ohad Ben-Cohen Subject: Re: [RFC 2/6] omap: iovmm: generic iommu api migration Date: Tue, 7 Jun 2011 16:46:26 +0300 Message-ID: References: <1307053663-24572-1-git-send-email-ohad@wizery.com> <201106071105.16262.laurent.pinchart@ideasonboard.com> <201106071326.53106.laurent.pinchart@ideasonboard.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Return-path: In-Reply-To: <201106071326.53106.laurent.pinchart@ideasonboard.com> Sender: linux-kernel-owner@vger.kernel.org To: Laurent Pinchart Cc: linux-media@vger.kernel.org, linux-omap@vger.kernel.org, linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, Hiroshi.DOYU@nokia.com, arnd@arndb.de, davidb@codeaurora.org, Joerg.Roedel@amd.com List-Id: linux-omap@vger.kernel.org Hi Laurent, On Tue, Jun 7, 2011 at 2:26 PM, Laurent Pinchart wrote: >> Right now we have a BUG_ON if pa is unaligned, but that can be changed >> if needed (do we want it to handle offsets ?). > > At least for the OMAP3 ISP we need to, as video buffers don't necessarily > start on page boundaries. Where do you take care of those potential offsets today ? Or do you simply ignore the offsets and map the entire page ? Seems like omap's iommu (mostly) rejects unaligned pa addresses, see: 4abb761749abfb4ec403e4054f9dae2ee604e54f "omap iommu: Reject unaligned addresses at setting page table entry" (this doesn't seem to cover 4KB entries though, only large pages, sections and super sections) > A separate patch is indeed needed, yes. As you're already working on iommu it > might be simpler if you add it to your tree. Sure, i'll send it. Thanks, Ohad.