From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tony Lindgren Subject: Re: [RFC/NOT FOR MERGING] HACK: add global/private timers for A9 Date: Wed, 3 Jun 2015 13:44:08 -0700 Message-ID: <20150603204407.GX30984@atomide.com> References: <1433363565-17725-1-git-send-email-balbi@ti.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from muru.com ([72.249.23.125]:55734 "EHLO muru.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932594AbbFCUoK (ORCPT ); Wed, 3 Jun 2015 16:44:10 -0400 Content-Disposition: inline In-Reply-To: <1433363565-17725-1-git-send-email-balbi@ti.com> Sender: linux-omap-owner@vger.kernel.org List-Id: linux-omap@vger.kernel.org To: Felipe Balbi Cc: Russell King , Linux ARM Kernel Mailing List , Linux OMAP Mailing List * Felipe Balbi [150603 13:36]: > > AM43xx, even though it's a single processor A9, it still has TWD and global > timer. I was doing some profiling with RT v4.0 and latency is 3.5x lower just > by switching from gptimer to twd/global. > > The only problem is that currently, is_smp() check prevents me from using twd > with AM43xx (that's why it's commented below, for testing purposes). > > In the hopes that we can start a, hopefully, small thread around the subject, > I'm sending this HACK which I used to get TWD and global timer enabled so I > could measure latencies with cyclictest. > > Is it so that TWD shouldn't be available on UP integrations of ARM's Cortex-A > processors ? > --- a/arch/arm/kernel/smp_twd.c > +++ b/arch/arm/kernel/smp_twd.c > @@ -388,8 +389,10 @@ static void __init twd_local_timer_of_register(struct device_node *np) > { > int err; > > +#if 0 > if (!is_smp() || !setup_max_cpus) > return; > +#endif > > twd_ppi = irq_of_parse_and_map(np, 0); > if (!twd_ppi) { Why don't you just check for the c-a9 revision here? If it's the UP processor then allow twd? Similar to what's done in global_timer_of_register? Regards, Tony