- 02 Dec, 2010 2 commits
-
-
Chris Wilson authored
With this change, every batchbuffer can use all available fences (save pinned and scanout, of course) without ever stalling the gpu! In theory. Currently the actual pipelined update of the register is disabled due to some stability issues. However, just the deferred update is a significant win. Based on a series of patches by Daniel Vetter. The premise is that before every access to a buffer through the GTT we have to declare whether we need a register or not. If the access is by the GPU, a pipelined update to the register is made via the ringbuffer, and we track the last seqno of the batches that access it. If by the CPU we wait for the last GPU access and update the register (either to clear or to set it for the current buffer). One advantage of being able to pipeline changes is that we can defer the actual updating of the fence register until we first need to access the object through the GTT, i.e. we can eliminate the stall on set_tiling. This is important as the userspace bo cache does not track the tiling status of active buffers which generate frequent stalls on gen3 when enabling tiling for an already bound buffer. Signed-off-by:
Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by:
Daniel Vetter <daniel.vetter@ffwll.ch>
-
Chris Wilson authored
Signed-off-by:
-
- 01 Dec, 2010 1 commit
-
-
Chris Wilson authored
Signed-off-by:
-
- 30 Nov, 2010 2 commits
-
-
Chris Wilson authored
This makes the various rings more consistent by removing the anomalous handing of the rendering ring execbuffer dispatch. Signed-off-by: -
Chris Wilson authored
Signed-off-by:
-
- 28 Nov, 2010 4 commits
-
-
Chris Wilson authored
... so that upon first use after resume we will reacquire the fence reg. Reported-by:
Keith Packard <keithp@keithp.com> Signed-off-by:
-
Chris Wilson authored
Conflicts: drivers/gpu/drm/i915/i915_gem.c
-
Chris Wilson authored
As the error occurred on the current object, it means that its state was not changed and so it should be excluded from the unwind. Reported-by:
-
Daniel Vetter authored
We don't track gpu flush request in any special way. So even with obj->write_domain == 0, a gpu flush might be outstanding but no yet executed. Even worse, the latest request might use the object only for reading. So and unconditional call to object_wait_rendering is needed for !pipelined. Hence revert that patch fully and untangle the flushing from the synchronization again. Reported-by:
-
- 25 Nov, 2010 7 commits
-
-
Chris Wilson authored
Besides the minimal improvement in reducing the execbuffer overhead, the real benefit is clarifying a few routines. Signed-off-by: -
Chris Wilson authored
A number of dragons have been seen lurking within the execbuffer code. The first step is then to isolate them from the rest and begin to scrutinise them in depth. Suggested by Daniel Vetter. Signed-off-by: -
Chris Wilson authored
Simply remove our accounting of objects inside the aperture, keeping only track of what is in the aperture and its current usage. This removes the over-complication of BUGs that were attempting to keep the accounting correct and also removes the overhead of the accounting on the hot-paths. Signed-off-by: -
Chris Wilson authored
... to benefit from the compiler checking that we remember to handle and propagate errors. Signed-off-by: -
Chris Wilson authored
Signed-off-by: -
Chris Wilson authored
With KMS, we can simply relinquish the fence when we idle the GPU and reassign it upon first use. Signed-off-by: -
Daniel Vetter authored
Not employed just yet... Signed-off-by:
-
- 24 Nov, 2010 4 commits
-
-
Chris Wilson authored
Commit d09c23de intended to add a 30ms delay to give the ADD time to detect any TVs connected. However, it used the sdvo->is_tv flag to do so which is dependent upon the previous detection result and not whether the output supports TVs. Signed-off-by:
-
Chris Wilson authored
Based on a patch by Daniel Vetter. Signed-off-by: -
Chris Wilson authored
Avoid evicting buffers that will be used later in the batch in order to make room for the initial buffers by pinning all bound buffers in a single pass before binding (and evicting for) fresh buffer. Signed-off-by: -
Joe Perches authored
Mark it so. Signed-off-by:
Joe Perches <joe@perches.com> Signed-off-by:
-
- 23 Nov, 2010 20 commits
-
-
Chris Wilson authored
On a few devices, like the Mac Mini, the CRT DDC pins are shared between the analog connector and the digital connector. In this scenario, rely on the EDID to determine if a digital panel is connected to the digital connector. Reported-and-tested-by:
Tino Keitel <tino.keitel@tikei.de> Signed-off-by:
-
Chris Wilson authored
Signed-off-by: -
Chris Wilson authored
... reduce the frequency of checking to further reduce the wakeups and CPU overhead. Signed-off-by: -
Chris Wilson authored
This used to check the precondition that all fences were to be located in a mappable area, redundant now as those two parameters are combined into one. After pinning, we assert that the buffer is bound into the desired region. Signed-off-by: -
Chris Wilson authored
The pipe control object is allocated by the device for the sole use of the render ringbuffer. Move this detail from the general code to the render ring buffer initialisation. Signed-off-by: -
Chris Wilson authored
Having seen the effects of erroneous fencing on the batchbuffer, a useful sanity check is to record the fence registers at the time of an error. Signed-off-by: -
Chris Wilson authored
drivers/char/agp/intel-gtt.c:340:48: warning: duplicate const Signed-off-by: -
Chris Wilson authored
Combining map_and_fenceable revealed a bug in i915_gem_object_gtt_size() in that it always computed the appropriate fence size for the object regardless of tiling state which caused us to over-allocate linear buffers when binding to the GTT. Signed-off-by: -
Chris Wilson authored
A glorified s/obj_priv/obj/ with a net reduction of over a 100 lines and many characters! Signed-off-by: -
Daniel Vetter authored
Signed-off-by:
-
Daniel Vetter authored
Just some minor shuffling to get rid of any agp traces in the exported functions. Signed-off-by:
-
Daniel Vetter authored
No more drm_*_agp in i915_gem.c! Signed-off-by:
-
Daniel Vetter authored
Its only user, intel-gtt.c is now gone. Cc: Dave Airlie <airlied@gmail.com> Signed-off-by:
-
Daniel Vetter authored
This still uses the agp functions to actually reinstate the mappings (with a gross hack to make agp cooperate), but it wires everything up correctly for the switchover. The call to agp_rebind_memory can be dropped because all non-kms drivers do all their rebinding on EnterVT. v2: Be more paranoid and flush the chipset cache after restoring gtt mappings. Signed-off-by:
-
Daniel Vetter authored
This is required to restore gtt mappings on resume when agp is gone. The right way to do this would be to make sturct drm_mm_node embeddable and use the allocation list maintained by the drm memory manager. But that's a bigger project. Getting rid of the per bo agp_mem will save more memory than this wastes, anyway. Signed-off-by:
-
Daniel Vetter authored
The intel drm calls the chipset functions now directly. Userspace never called the corresponding ioctl, hence it can be killed, too. Cc: Dave Airlie <airlied@gmail.com> Signed-off-by:
-
Daniel Vetter authored
No longer used. Cc: Dave Airlie <airlied@gmail.com> Signed-off-by:
-
Daniel Vetter authored
Signed-off-by:
-
Daniel Vetter authored
... and a few other defines. Signed-off-by:
-
Daniel Vetter authored
Now the intel-gtt.c rewrite is complete! Signed-off-by:
-
