Home | History | Annotate | Download | only in drm
History log of /src/sys/external/bsd/drm2/include/drm/intel-gtt.h
RevisionDateAuthorComments
 1.10  19-Dec-2021  riastradh i915: Make intel_gtt_get prototype match Linux.
 1.9  19-Dec-2021  riastradh i915: ggtt
 1.8  19-Dec-2021  riastradh Update intel gtt API.

TODO: Find where the stolen memory base is in agp_i810.
 1.7  27-Aug-2018  riastradh Linux uses uint64 for these parameters now, so follow suit.
 1.6  27-Aug-2018  riastradh Call it intel_gtt_insert_sg_entries for expedience.

It uses a bus_dmamap, not a Linux scatterlist a.k.a. sg, but
otherwise it functions the same way and this avoids patching
upstream.
 1.5  06-Mar-2015  riastradh branches: 1.5.16; 1.5.18;
Pass cache-related flags through to the GTT on pre-SNB devices.

I had assumed for ages this would increase the amount of caching and
thereby increase the chance of stale caches leading to rendering
glitches. But apparently I was wrong, and failing to pass these
through was causing all sorts of problems!
 1.4  16-Jul-2014  riastradh branches: 1.4.2; 1.4.4; 1.4.6;
Make it build and boot on my test machines.

Screen blanks on boot on the Ivy Bridge system with

DRM error in cpt_serr_int_handler: PCH transcoder A FIFO underrun

But after that everything is OK. Appears to be an upstream problem.
To investigate...

I think there's a cache flushing issue somewhere -- there are little
display artefacts on my T60.
 1.3  28-May-2014  riastradh Explain the fields of struct intel_gtt for future reference.
 1.2  18-Mar-2014  riastradh branches: 1.2.2; 1.2.4; 1.2.6;
Merge riastradh-drm2 to HEAD.
 1.1  24-Jul-2013  riastradh branches: 1.1.2;
file intel-gtt.h was initially added on branch riastradh-drm2.
 1.1.2.3  05-Mar-2014  riastradh Oops -- define struct intel_gtt::do_idle_maps.

Missed this in last commit.
 1.1.2.2  08-Sep-2013  riastradh Rework Intel GTT abstraction to use bus_dma.
 1.1.2.1  24-Jul-2013  riastradh Add stub <drm/intel-gtt.h>, forgotten a while ago.
 1.2.6.2  22-May-2014  yamt sync with head.

for a reference, the tree before this commit was tagged
as yamt-pagecache-tag8.

this commit was splitted into small chunks to avoid
a limitation of cvs. ("Protocol error: too many arguments")
 1.2.6.1  18-Mar-2014  yamt file intel-gtt.h was added on branch yamt-pagecache on 2014-05-22 11:40:56 +0000
 1.2.4.2  18-May-2014  rmind sync with head
 1.2.4.1  18-Mar-2014  rmind file intel-gtt.h was added on branch rmind-smpnet on 2014-05-18 17:46:01 +0000
 1.2.2.1  10-Aug-2014  tls Rebase.
 1.4.6.1  06-Apr-2015  skrll Sync with HEAD
 1.4.4.3  03-Dec-2017  jdolecek update from HEAD
 1.4.4.2  20-Aug-2014  tls Rebase to HEAD as of a few days ago.
 1.4.4.1  16-Jul-2014  tls file intel-gtt.h was added on branch tls-maxphys on 2014-08-20 00:04:21 +0000
 1.4.2.1  17-Mar-2015  riz Pull up following revision(s) (requested by snj in ticket #590):
sys/external/bsd/drm2/i915drm/intel_gtt.c: revision 1.5
sys/external/bsd/drm2/drm/drm_drv.c: revision 1.15
sys/external/bsd/drm2/dist/drm/i915/i915_gem.c: revision 1.28
sys/external/bsd/drm2/dist/drm/nouveau/core/subdev/clock/nouveau_subdev_clock_nv50.c: revision 1.3
sys/dev/pci/agp_i810.c: revision 1.115
sys/dev/pci/agp_i810.c: revision 1.116
sys/external/bsd/drm2/include/drm/intel-gtt.h: revision 1.5
sys/dev/pci/agp_i810.c: revision 1.117
sys/external/bsd/drm2/drm/drm_gem_vm.c: revision 1.6
sys/dev/pci/agp_i810var.h: revision 1.6
Issue a write barrier after updating the GTT.
Linux never used to do this...until a month:
<a rel="nofollow" href="https://bugs.freedesktop.org/show_bug.cgi?id=88191">https://bugs.freedesktop.org/show_bug.cgi?id=88191</a>
commit 983d308cb8f602d1920a8c40196eb2ab6cc07bd2
Author: Chris Wilson &lt;chris%chris-wilson.co.uk@localhost&gt;
Date: Mon Jan 26 10:47:10 2015 +0000
agp/intel: Serialise after GTT updates
Include &lt;sys/atomic.h&gt; for membar_producer.
(Why didn't this fail in my build?)
Pass cache-related flags through to the GTT on pre-SNB devices.
I had assumed for ages this would increase the amount of caching and
thereby increase the chance of stale caches leading to rendering
glitches. But apparently I was wrong, and failing to pass these
through was causing all sorts of problems!
Dedup the NetBSD portion of the code (ok Riastradh), no functional change.
Don't return events that are too large and leave them in the list.
Apply access control to gem mmap.
fix gcc is stupid.
 1.5.18.1  10-Jun-2019  christos Sync with HEAD
 1.5.16.1  06-Sep-2018  pgoyette Sync with HEAD

Resolve a couple of conflicts (result of the uimin/uimax changes)

RSS XML Feed