On Sat, Apr 09, 2011 at 11:31:14PM +0100, Chris Wilson wrote:
> On Sat, 9 Apr 2011 13:31:22 -0700, Ben Widawsky wrote:
> > +*
> > +* Intelligent users of the interface may do a force_wake_get() followed
> > +* by many register reads and writes, knowing that the reference count
> > +
On 04/09/2011 04:29 PM, Ian Pilcher wrote:
> I have cloned
> git://anongit.freedesktop.org/git/xorg/driver/xf86-video-intel, but git
> show is unable to find the commits in question. I would
> very much appreciate any help tracking down the following commits:
Never mind. Managed to find them (wi
On Sat, 9 Apr 2011 13:31:22 -0700, Ben Widawsky wrote:
> + *
> + * Intelligent users of the interface may do a force_wake_get() followed
> + * by many register reads and writes, knowing that the reference count
> + * is already incremented. So we do not want to warn on those.
Fedora 15 recently pushed a test update that caused some problems on my
system. The update is basically a single patch file that appears to be
built from several git commits. I would like to test the commits
individually to see which one is causing the problem.
I have cloned
git://anongit.freede
This patch will likely produce much fewer warnings, but perhaps hide
some bugs in the driver. Any warnings while using this patch are
extremely likely to cause problems, while warnings without this patch
are also driver bugs, but much less likely to be causing issues. Without
this patch we may also
Provide debugfs access to the refcounted forcewake. This allows a
userspace utility to access some of those hard to reach registers on
newer GPUs. The interface is root-only.
The interface is referred to as a forcewake lock. The term lock refers
to the synchronization between software and hardware
New refcounting mechanism for forcewake. The idea is to take away the
need to hold struct_mutex for the duration of register reads, and only
need to hold it to get a reference count. A possible benefit would shave
off some time in actually waking the GPU if it's already awake (a couple
of extra reg
Moved the macros around to properly do reads and writes for the given
gpu. This is to address special requirements for gen6 (SNB) reads and
writes.
Signed-off-by: Ben Widawsky
---
drivers/gpu/drm/i915/i915_drv.h | 56 ++
drivers/gpu/drm/i915/intel_ringbuffer
The request to test, and report the warnings is still desired.
These address all of Chris' comments from IRC (I think). I tried to put
the reasoning in the code comments, as well as commits; but I'll add it
here for completeness.
Simplify the acquisition of the forcewake lock by removing the for
Provide debugfs access to the refcounted forcewake. This allows a
userspace utility to access some of those hard to reach registers on
newer GPUs. The interface is root-only.
The interface is referred to as a forcewake lock. The term lock refers
to the synchronization between software and hardware
New refcounting mechanism for forcewake. The idea is to take away the
need to hold struct_mutex for the duration of register reads, and only
need to hold it to get a reference count. A possible benefit would shave
off some time in actually waking the GPU if it's already awake (a couple
of extra reg
Moved the macros around to properly do reads and writes for the given
gpu. This is to address special requirements for gen6 (SNB) reads and
writes.
Signed-off-by: Ben Widawsky
---
drivers/gpu/drm/i915/i915_drv.h | 56 ++
drivers/gpu/drm/i915/intel_ringbuffer
___
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
GIT: [Intel-gfx] [PATCH 1/4] drm/i915: proper use of forcewake
GIT: [Intel-gfx] [PATCH 2/4] drm/i915: refcounts for forcewake
GIT: [Intel-gfx] [PATCH 3/4] drm/i915: userspace interface to the forcewake
refcount
GIT: [Intel-gfx] [PATCH 4/4] drm/i915: optional fewer warning patch
___
The request to test, and report the warnings is still desired.
These address all of Chris' comments from IRC (I think). I tried to put
the reasoning in the code comments, as well as commits; but I'll add it
here for completeness.
Simplify the acquisition of the forcewake lock by removing the for
Lan, Hai would like to recall the message, "Q1 RC2 test report for SNB H264
encoding driver".
___
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
16 matches
Mail list logo
