Needed to make sure we can enter/exit RC6 properly.
v2: move to modeset_init since reset in init_clock_gating is too early
Cc: James Kukunas
Cc: Arjan van de Ven
Signed-off-by: Jesse Barnes
---
drivers/gpu/drm/i915/i915_dma.c |7 +++
1 file changed, 7 insertions(+)
diff --git a/drive
I wasn't able to reproduce the performance hit after reset you guys were
seeing, but did see that the way I was doing reset may have been causing
more general trouble (I got GPU hangs at init) which could explain what
you were seeing.
So please give this patch a try and see if it still allows you
On Tue, Nov 27, 2012 at 08:34:58PM +0200, ville.syrj...@linux.intel.com wrote:
> From: Ville Syrjälä
>
> As per Chris Wilson's suggestion make
> i915_gem_execbuffer_wait_for_flips() go away.
>
> This was used to stall the GPU ring while there are pending
> page flips involving the relevant BO. I
On Tue, Nov 27, 2012 at 08:34:56PM +0200, ville.syrj...@linux.intel.com wrote:
> From: Ville Syrjälä
>
> intel_pipe_set_base() never actually waited for any pending page flips
> on the CRTC. It looks like it tried to, by calling intel_finish_fb() on
> the current front buffer. But the pending fli
On Tue, Nov 27, 2012 at 08:34:55PM +0200, ville.syrj...@linux.intel.com wrote:
> From: Ville Syrjälä
>
> From BSpec:
> "If the Ring Buffer Head Pointer and the Tail Pointer are on the same
> cacheline, the Head Pointer must not be greater than the Tail
> Pointer."
>
> The easiest way to enforce
On Mon, 26 Nov 2012 21:52:54 -0800
Ben Widawsky wrote:
> This bug was introduced by me:
> commit e76e9aebcdbfebae8f4cd147e3c0f800d36e97f3
> Author: Ben Widawsky
> Date: Sun Nov 4 09:21:27 2012 -0800
>
> drm/i915: Stop using AGP layer for GEN6+
>
> The existing code uses memset_io which f
On Wed, 28 Nov 2012 11:13:14 +0800
Daniel J Blueman wrote:
> Hi Daniel/Ben,
>
> On stock 3.7-rc7, when resuming my Ivy Bridge laptop from suspend, the
> kernel logs:
>
> [drm:__gen6_gt_force_wake_mt_get] *ERROR* Timed out waiting for
> forcewake to ack request.
> [drm:__gen6_gt_wait_for_thread_
On Fri, 23 Nov 2012 16:51:09 + (UTC)
РоманМельник wrote:
> > It could be CABC (Content Adaptive Backlight Control) which is a similar
> > technology but is implemented fully in hardware, in the panel. How you
> > can disable (and IF you can disable it) depends completely on the hardware.
> >
i915_gem_handle_seqno_wrap() will zero all sync_seqnos but as the
wrap can happen inside ring->sync_to(), pre wrap seqno was
carried over and overwrote the zeroed sync_seqno.
When wrap is handled, all outstanding requests will be retired and
objects moved to inactive queue, causing their last_read
