From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tomi Valkeinen Subject: Re: [PATCH 05/33] drm/omap: partial workaround for DRA7 DMM errata i878 Date: Wed, 24 Feb 2016 11:14:15 +0200 Message-ID: <56CD7467.60902@ti.com> References: <1455875288-4370-1-git-send-email-tomi.valkeinen@ti.com> <1455875288-4370-6-git-send-email-tomi.valkeinen@ti.com> <5240664.Dy4C1HiFai@avalon> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0898519302==" Return-path: Received: from devils.ext.ti.com (devils.ext.ti.com [198.47.26.153]) by gabe.freedesktop.org (Postfix) with ESMTPS id E08F56E065 for ; Wed, 24 Feb 2016 13:52:39 +0000 (UTC) In-Reply-To: <5240664.Dy4C1HiFai@avalon> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" To: Laurent Pinchart Cc: dri-devel@lists.freedesktop.org List-Id: dri-devel@lists.freedesktop.org --===============0898519302== Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="NsCdcKSjU4FiStfsov7vV8ArAuucCiOca" --NsCdcKSjU4FiStfsov7vV8ArAuucCiOca Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Hi, On 23/02/16 23:57, Laurent Pinchart wrote: > Hi Tomi, >=20 > Thank you for the patch. Thanks for review, good points. I'll drop this patch from the series for now. The reason being, this issue is rather difficult to reproduce and test, so any changes I do to patch this will take time to verify. I'll address the comments later. > On Friday 19 February 2016 11:47:40 Tomi Valkeinen wrote: >> Errata i878 says that MPU should not be used to access RAM and DMM at >> the same time. As it's not possible to prevent MPU accessing RAM, we >> need to access DMM via a proxy. >> >> This patch changes DMM driver to access DMM registers via sDMA. Instea= d >> of doing a normal readl/writel call to read/write a register, we use >> sDMA to copy 4 bytes from/to the DMM registers. >> >> This patch provides only a partial workaround for i878, as not only DM= M >> register reads/writes are affected, but also accesses to the DMM mappe= d >> buffers (framebuffers, usually). >=20 > Will this patch really improve the situation if the DMM mapping is acce= ssed=20 > anyway ? Depends. For TI environments it helps, as we don't draw with the CPU. If there's drawing done with CPU, the issue may still happen. I have never seen it happen in normal situations, though, but I did manage to trigger it with explicit stress testing. Also, I don't have any good solution to the framebuffer part... Except doing a memcpy, ruining the performance. Tomi --NsCdcKSjU4FiStfsov7vV8ArAuucCiOca Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQIcBAEBCAAGBQJWzXRoAAoJEPo9qoy8lh71gxMQAKtcWl2oDyVFkIAXB1MMpaGD iUj8hI4KhAf3o4ZpM5ZrS7s3OYLbDmC8gJeCP7GdKinoJeZCF4KDOuZjyXGfHP4A yXbjtwTUgssaTIvaKGGyh1k6VbWTS8cjejMYJPG6P+PDiibd+YHzNoYNtPe4DIHP yUJRfvxFZYtsnKB0133l8fC8r/AOuaEV0g5TiNeCStsKDHOuBCNLqMSmLfN7D+u8 w1EVg8BPINyObxs+c9TDO+Agsacyy4KWi+t2BLa613KUIiRGQWj47Q7oNj9yt1lq RGtwVmKU49e6X0z9n1OkmVTbEGYLVhwnvGJ2lYcG24B587M3TTEm5UqGrwTRQIqg b3Q5Yy5n99j5nwdgnMFAJ49m8Ea6nlwwCGadm3iCCrlKUAADtVMwhncm14L+phec sh5RyxfGVQaSYfK8mTvbJ7wPniFE0Vs9COaUv/50T7M6V59w2nQgpkjtBSI4zoKj +mCm+ISb8UQneahZxVG0Zx25/FRCGufRsXyeZPMWI6SBmdfGV49aOUCx0kn7AiVg lu8YDWc+n4buyBzhQ08oek+A3SiRszx5Me1xCfMn5XLZjnsdS7RTxto9TKLN4Oio Wtk6GJNogXMKvTa+pMXPXk4tKTbHsobxSOH/qKBw1IY1NXvdQECaBnlMmRTd5YJg sMstHTRI6d/Aj6XJ9nKc =q7H5 -----END PGP SIGNATURE----- --NsCdcKSjU4FiStfsov7vV8ArAuucCiOca-- --===============0898519302== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KZHJpLWRldmVs IG1haWxpbmcgbGlzdApkcmktZGV2ZWxAbGlzdHMuZnJlZWRlc2t0b3Aub3JnCmh0dHBzOi8vbGlz dHMuZnJlZWRlc2t0b3Aub3JnL21haWxtYW4vbGlzdGluZm8vZHJpLWRldmVsCg== --===============0898519302==--