From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?UTF-8?B?Q2hyaXN0aWFuIEvDtm5pZw==?= Subject: Re: [PATCH 1/3] drm/radeon: stop poisoning the GART TLB Date: Thu, 19 Jun 2014 11:45:57 +0200 Message-ID: <53A2B155.4000001@vodafone.de> References: <1401888598-1961-1-git-send-email-deathsimple@vodafone.de> <5398218A.4040104@vodafone.de> <53998D99.6050008@vodafone.de> <539B1CA0.6010600@vodafone.de> <539D9601.8090308@vodafone.de> <53A2415D.6020808@daenzer.net> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="------------050509020109080807020201" Return-path: Received: from pegasos-out.vodafone.de (pegasos-out.vodafone.de [80.84.1.38]) by gabe.freedesktop.org (Postfix) with ESMTP id 01C2F6E858 for ; Thu, 19 Jun 2014 02:46:11 -0700 (PDT) Received: from localhost (localhost.localdomain [127.0.0.1]) by pegasos-out.vodafone.de (Rohrpostix2 Daemon) with ESMTP id E277560AD64 for ; Thu, 19 Jun 2014 11:46:10 +0200 (CEST) Received: from pegasos-out.vodafone.de ([127.0.0.1]) by localhost (rohrpostix2.prod.vfnet.de [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id aUro7eZRQ71e for ; Thu, 19 Jun 2014 11:46:05 +0200 (CEST) In-Reply-To: <53A2415D.6020808@daenzer.net> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" To: =?UTF-8?B?TWljaGVsIETDpG56ZXI=?= , Alex Deucher Cc: dri-devel List-Id: dri-devel@lists.freedesktop.org This is a multi-part message in MIME format. --------------050509020109080807020201 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: quoted-printable Am 19.06.2014 03:48, schrieb Michel D=C3=A4nzer: > On 15.06.2014 21:48, Christian K=C3=B6nig wrote: >> Am 13.06.2014 23:31, schrieb Alex Deucher: >>> On Fri, Jun 13, 2014 at 11:45 AM, Christian K=C3=B6nig >>> wrote: >>>> Hi Marek, >>>> >>>> ah, yes! Piglit in combination with that patch can indeed crash the = box. >>>> >>>> Going to investigate now that I can reproduce it. >>> I wonder if it's a clockgating issue with the MC or BIF? You might >>> try adjusting the rdev->cg_flags (try setting it to 0) in >>> radeon_asic.c or disabling dpm. >> Unfortunately that was just a false alarm. >> >> I was just on a branch which didn't had the "stop poisoning the GART >> TLB" patch, after applying this patch I can again let piglit run for t= he >> whole night without a lockup. >> >> No idea what goes wrong when Marek runs piglit, but 3.15.0+"stop >> poisoning the GART TLB"+"force_gtt" is rock solid here. > FWIW, 3.15 doesn't survive piglit on my Bonaire either, but 3.14 is > fine. 3.15 seems stable on Kaveri though, but I haven't tried the > force_gtt patch on that yet. Yeah, I think it's just me who has a stable system with 3.15 and that=20 annoys me quite a bit. No idea what's the difference. What versions of LLVM/Mesa/Piglit are you=20 using for the test? > > There have also been a number of bug reports about stability regression= s > in 3.15 on various SI and CIK cards. It seems likely that at least some > of those are related to this issue as well. > > If we can't figure out the problem soon, we probably need to revert the > 'Use normal BOs for page tables' and dependent changes at least for 3.1= 5.y? I thought about this for the whole 3.15 release cycle, but decided=20 against it. But what we could do is applying the attached trivial patch,=20 it pins down the page tables and so pretty much reverts to the old behavi= or. I think even when we revert to the old code we have a couple of unsolved=20 problems with the VM support or in the driver in general where we should=20 try to understand the underlying reason for it instead of applying more=20 workarounds. Going to try harder crashing my 3.15 system, Christian. --------------050509020109080807020201 Content-Type: text/x-diff; name="0001-drm-radeon-pin-down-page-tables.patch" Content-Disposition: attachment; filename="0001-drm-radeon-pin-down-page-tables.patch" Content-Transfer-Encoding: quoted-printable >>From 43973a95578c3ef0f20d3ad997549ef588ff0f29 Mon Sep 17 00:00:00 2001 From: =3D?UTF-8?q?Christian=3D20K=3DC3=3DB6nig?=3D Date: Thu, 19 Jun 2014 11:40:38 +0200 Subject: [PATCH] drm/radeon: pin down page tables MIME-Version: 1.0 Content-Type: text/plain; charset=3DUTF-8 Content-Transfer-Encoding: 8bit Avoid evicting them from VRAM for now. Signed-off-by: Christian K=C3=B6nig --- drivers/gpu/drm/radeon/radeon_vm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/= radeon_vm.c index 4c18346..3029aad 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -368,7 +368,7 @@ static int radeon_vm_clear_bo(struct radeon_device *r= dev, if (r) return r; =20 - r =3D ttm_bo_validate(&bo->tbo, &bo->placement, true, false); + r =3D radeon_bo_pin(bo, RADEON_GEM_DOMAIN_VRAM, NULL); if (r) goto error; =20 --=20 1.9.1 --------------050509020109080807020201 Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ dri-devel mailing list dri-devel@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/dri-devel --------------050509020109080807020201--