Re: [Intel-gfx] [PATCH 3/4] drm/i915: Insert a full mb() before reading the seqno from the status page

2013-01-19 Thread Chris Wilson
On Fri, 19 Oct 2012 13:52:49 -0700, Jesse Barnes wrote: > On Fri, 19 Oct 2012 21:40:17 +0100 > Chris Wilson wrote: > > > On Thu, 11 Oct 2012 12:46:00 -0700, Jesse Barnes > > wrote: > > > On Tue, 9 Oct 2012 19:24:39 +0100 > > > Chris Wilson wrote: > > > > > > > Hopefully this will reduce a

Re: [Intel-gfx] i915-related and general system freezes with specific kernel config // IOMMU

2013-01-19 Thread Daniel Vetter
Hi Mihai, You have a gen4.5 chipset which is known to be utterly broken for IOMMU+intel gpu. Looks like a few distros started enabling IOMMU by default (fc18 has similar issues) and we've never added the proper quirks. See https://bugzilla.kernel.org/show_bug.cgi?id=51921 for a proposed patch to f

Re: [Intel-gfx] [PATCH 2/4] drm/i915: Only apply the mb() when flushing the GTT domain during a finish

2013-01-19 Thread Daniel Vetter
On Thu, Oct 11, 2012 at 12:43:42PM -0700, Jesse Barnes wrote: > On Tue, 9 Oct 2012 19:24:38 +0100 > Chris Wilson wrote: > > > Now that we seem to have brought order to the GTT barriers, the last one > > to review is the terminal barrier before we unbind the buffer from the > > GTT. This needs to

Re: [Intel-gfx] [PATCH] drm/i915: re-add dropped dma_mask configuration

2013-01-19 Thread Daniel Vetter
On Fri, Jan 18, 2013 at 07:18:19PM -0800, Ben Widawsky wrote: > I'm pretty sure without this, and with DMAR, things explode > spectacularly. I got to this patch via bisecting broken i-g-t on my > machine. > > If I had wired ethernet, I would figure out exactly what's failing with > netconsole. To

Re: [Intel-gfx] Updated testing

2013-01-19 Thread Daniel Vetter
On Fri, Jan 18, 2013 at 09:51:14PM +0100, Daniel Vetter wrote: > Hi all, > > Despite the longer cycle of four weeks, not much going on ... Highlights: > - Broadcast RBG improvements and reduced color range fixes from Ville > - Ben is on a "kill legacy gtt code for good" spree, first pile of patche

Re: [Intel-gfx] i915-related and general system freezes with specific kernel config // IOMMU

2013-01-19 Thread Daniel Vetter
On Sat, Jan 19, 2013 at 5:13 PM, Mihai Moldovan wrote: >> [...] and we've never added the proper >> quirks. See https://bugzilla.kernel.org/show_bug.cgi?id=51921 for a >> proposed patch to fix this (i.e. automatically set >> intel_iommu=igfx_off for affected platfroms). Testing highly welcome. > >

Re: [Intel-gfx] i915-related and general system freezes with specific kernel config // IOMMU

2013-01-19 Thread Daniel Vetter
On Sat, Jan 19, 2013 at 5:26 PM, Mihai Moldovan wrote: > The current patch errors out on my while compiling as quirk_iommu_rwbf is not > yet defined at that place. Oops, attached an old patch, updated one should work better. -Daniel -- Daniel Vetter Software Engineer, Intel Corporation +41 (0) 7

Re: [Intel-gfx] i915-related and general system freezes with specific kernel config // IOMMU

2013-01-19 Thread Mihai Moldovan
* On 19.01.2013 02:27 PM, Daniel Vetter wrote: > You have a gen4.5 chipset which is known to be utterly broken for > IOMMU+intel gpu. Nice description for what I'm seeing. ;) After some more hours of uptime I'm inclined to say, that "intel_iommu=off iommu=off" fixes my random freezes as well. Ala

Re: [Intel-gfx] i915-related and general system freezes with specific kernel config // IOMMU

2013-01-19 Thread Mihai Moldovan
* On 19.01.2013 05:13 PM, Mihai Moldovan wrote: > * On 19.01.2013 02:27 PM, Daniel Vetter wrote: >> You have a gen4.5 chipset which is known to be utterly broken for >> IOMMU+intel gpu. > Nice description for what I'm seeing. ;) > > After some more hours of uptime I'm inclined to say, that "intel_i

Re: [Intel-gfx] external screen goes black

2013-01-19 Thread Daniel Vetter
Hi Jonathan, Can you please boot with drm.debug=0xe and then attach the complete dmesg once right after boot, and once after the screen went black? Thanks, Daniel On Sun, Jan 20, 2013 at 1:38 AM, Jonathan Adamczewski wrote: > Hardware is a Dell XPS laptop, xorg log reports "Integrated Graphics

Re: [Intel-gfx] [RFC] [PATCH] quick_dump: A dump utility different than reg_dumper

2013-01-19 Thread Ben Widawsky
On Sat, Sep 22, 2012 at 08:05:04PM +0200, Daniel Vetter wrote: > On Fri, Sep 21, 2012 at 12:46:05PM -0700, Ben Widawsky wrote: > > intel_reg_dumper is cool. However, doing bit decoding and dealing with > > moving registers from generation to generation (and in some cases just > > steppings) becomes

[Intel-gfx] [PATCH 1/3] [RFC] drm/i915: Create a vtable for i915 gtt

2013-01-19 Thread Ben Widawsky
Before going further I wanted to run these 3 patches by the ML... The GTT handling has changed from generation to generation. There was a particularly large shift around the gen5 time frame. The GTT itself those provides a few core functions which make it a nice candidate for a dispatch table. A s

[Intel-gfx] [PATCH 2/3] [RFC] drm/i915: Resume dissecting intel_gtt

2013-01-19 Thread Ben Widawsky
With the GMCH call in our dispatch table, we can now cut away two of the remaining members in the intel_gtt shared struct. Signed-off-by: Ben Widawsky --- drivers/char/agp/intel-gtt.c | 20 +--- drivers/gpu/drm/i915/i915_drv.h| 1 + drivers/gpu/drm/i915/i915_ge

[Intel-gfx] [PATCH 3/3] [RFC] drm/i915: With the vtable, intel_gtt is useless

2013-01-19 Thread Ben Widawsky
Signed-off-by: Ben Widawsky --- drivers/char/agp/intel-gtt.c| 18 +- drivers/gpu/drm/i915/i915_drv.h | 2 -- drivers/gpu/drm/i915/i915_gem_gtt.c | 21 ++--- include/drm/intel-gtt.h | 6 +- 4 files changed, 12 insertions(+), 35 deletion