From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Nathan Monson" Subject: Re: omapfb: help from userspace Date: Thu, 9 Oct 2008 10:55:11 -0700 Message-ID: References: <13B9B4C6EF24D648824FF11BE89671620365B58844@dlee02.ent.ti.com> <20081009124357.GF26230@atomide.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: Received: from qw-out-2122.google.com ([74.125.92.24]:20234 "EHLO qw-out-2122.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754474AbYJIRzN (ORCPT ); Thu, 9 Oct 2008 13:55:13 -0400 Received: by qw-out-2122.google.com with SMTP id 3so45353qwe.37 for ; Thu, 09 Oct 2008 10:55:11 -0700 (PDT) In-Reply-To: <20081009124357.GF26230@atomide.com> Content-Disposition: inline Sender: linux-omap-owner@vger.kernel.org List-Id: linux-omap@vger.kernel.org To: Tony Lindgren Cc: "Woodruff, Richard" , "linux-omap@vger.kernel.org List" , "TK, Pratheesh Gangadhar" On Thu, Oct 9, 2008 at 5:43 AM, Tony Lindgren wrote: > Nathan, good to hear that the SO mode helps. But since you seem to > have it easily reproducable.. Reproducing is as easy as applying the DSP Bridge kernel patches and then running the 'ping.out' sample like this: while true; do ping.out; done > Could you try the following patch based on RMK's earlier patch > without the strongly ordered patch and see if that makes any > difference? Maybe it lasted a few seconds longer, or maybe it was luck, but in any case it eventually went into an IRQ -33 loop even with this patch. > If this patch alone does not do anything, maybe try reading back > something from the dsp interrupt registers after write also > in the dsp interrupt handler? I will look into this and let you know. > Also you might want to read through the thread linked in the > patch description. > > And, if that still does not work, I'm suspecting that in some cases > write-read is not enough, and only write-write ensures that it gets > posted. Some ARM docs say that writes are only posted relative to > other writes, but I don't know if it can be really that way. Should I change the patch you sent me to do write write? > At least we have at least one hack like that in the > drivers/mmc/host/omap.c. > > Anyways, it would be nice to solve this issue for good. The problem > has been making it easily reproducable. At least I have a workaround for now. It's good to be able to get DSP work done. - Nathan