From mboxrd@z Thu Jan 1 00:00:00 1970 Date: Fri, 4 Jul 2014 09:19:39 +0200 From: Arnaud Degroote Message-ID: <20140704071939.GA12028@dmia-degroote.isae.fr> References: <7016-53b1af80-3d5-7f54e300@12077259> <53B1B529.9040106@xenomai.org> <20140701083910.GA28764@dmia-degroote.isae.fr> <53B27E5B.10507@xenomai.org> <20140701155123.GA5547@dmia-degroote.isae.fr> <53B30A78.40605@xenomai.org> <20140702114142.GA13439@dmia-degroote.isae.fr> <53B44879.5020203@xenomai.org> <20140703083807.GA10654@dmia-degroote.isae.fr> <53B54DEA.9020306@xenomai.org> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <53B54DEA.9020306@xenomai.org> Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Subject: Re: [Xenomai] Support of Beagleboard xm rev C on 3.14-ipipe List-Id: Discussions about the Xenomai project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Gilles Chanteperdrix Cc: xenomai@xenomai.org On 03/Jul - 14:34, Gilles Chanteperdrix wrote: > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA1 > > On 07/03/2014 10:38 AM, Arnaud Degroote wrote: > > On 02/Jul - 19:59, Gilles Chanteperdrix wrote: > >> -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 > >> > >> > >> Well, this sucks, posted writes increase the timer programming > >> latency. > >> > >> Does the latency test run correctly with this patch? > > > > Yes, the latency test seems to work properly. > > That is strange, because the Xenomai timer also uses non-posted writes. > > > > > I need to investigate a bit more, because the kernel without the > > patch seems to work properly with a different uboot (the one for my > > gumstix) while it hangs with the uboot for my beagleboard. > > Perhaps the u-boot which works implement some workaround for processor > errata, which the u-boot which does not work does not implement? I don't understand where the difference comes from. I tried with several variants of u-boot, with the same patchlevel, and it always works with 'omap_overo_config' and always hangs with 'omap_beagle_config'. I carefully read the two board code and make several hack in beagle one to reduce diff with overo, but was not able yet to reproduce the 'correct behaviour'. Unfortunately, I lack time to continue investigation, I will go for the 'posted' hack for the moment and will open an issue in my job bugtracker. I may try also with uboot + dts. Anyway, thanks a lot for your help Gilles. I will let you know if I make significant progress on this issue. Best regards, -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 490 bytes Desc: Digital signature URL: