summaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Collapse)Author
2012-08-24sna: Submit the partial batch before throttlingChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-24sna: Allow the batch to be flushed if the GPU is idle upon a context switchChris Wilson
Submit early, submit often in order to keep the GPU busy. As always we trade off CPU overhead versus concurrency. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-24sna: Correct a pair of DBG messagesChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-23sna: Tidy up users of __kgem_bo_is_busy()Chris Wilson
A lot of callsites had not been converted to the common function. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-23sna: Use a temporary userptr mapping for a large upload into a busy targetChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-23sna: Flush the batch if it contains any DRI pixmapsChris Wilson
This fixes a regression from commit 02963f489b177d0085006753e91e240545933387 Author: Chris Wilson <chris@chris-wilson.co.uk> Date: Sun Aug 19 15:45:35 2012 +0100 sna: Only submit the batch if flushing a DRI client bo which made the presumption that we called sna_add_flush_pixmap() for every DRI pixmap that we used. However, that is only called for the dirty pixmaps, any native exported pixmap only marks the batch as requiring a flush. So in those cases we always need to submit the batch if it contains an exported DRI pixmap. Reported-by: chr.ohm@gmx.net Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=53967 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-23sna: Mark the CPU damage as needing flushing for DRI buffersChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-22sna: Flush before adding any SHM pixmap into the batchChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-22sna: Only use the GPU for an active CPU bo unless forcedChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-22sna: If we cannot use the CPU bo along a render pathway, promote to GPUChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-22sna: Convert to using IGNORE_CPU flag rather than complicating the CPU damageChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-22sna: Assert that the CPU bo is not used if the GPU is clearChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-22sna: Make sure the opposite damage is destroyed after reducing to allChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-22sna: Discard a no-longer-used GPU bo after moving to the CPU domainChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-22sna: Balance CPU bo accounting for SHM pixmapsChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-21sna: Display still resident memory in inactive/snoop caches under DEBUG_MEMORYChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-21sna: Add a DBG to log pixmap destructionChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-21sna: Fix the assertion for tracking proxies in the batchChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-21sna: Mark all levels of a proxy as dirtyChris Wilson
So that if we write to a surface through one view, we make sure that the sample cache is invalidated for all future views. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-21sna/gen6+: Only mark the dst as dirty again if it already is in the batchChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna/gen3: Fix assertion to check the freshly allocated vertex boChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: Allow target bo promotion to GPU even on old architecturesChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: Assign a unique id to snoopable CPU boChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna/gen3: Convert to sna_drawable_use_bo()Chris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: Trim a parameter from kgem_bo_mark_dirty() and add some assertionsChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: Keep a stash of the most recently allocated requestsChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: A few more buffer cache management assertionsChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20Check that the module that indeed i915 before using custom ioctlsChris Wilson
Thanks to Adam Jackson for pointing me towards drmGetVersion() and Julien Cristau for saying "Yuck!" Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20Only open the matching BusID and not the first namedChris Wilson
If you pass a name to drmOpen() it will attempt to open any device corresponding to that name if it first fails to open the device corresponding to the BusID. Obviously we want the failure from opening the specified device in order to prevent wrongly opening the first found device multiple times. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: Add a couple of buffer cache management assertionsChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: Remove confusing is_cpu()Chris Wilson
The only real user now has its own heuristics, so convert the remaining users over to !is_gpu(). Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: Refine decision making for maybe-inplace trapezoidsChris Wilson
In particular, we want to avoid preferentially taking the CPU paths when it may force any migration (including clear). Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: Correct ordering of calls to memcpy for BLT cpu composite pathsChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20Missing includes for b5b76ad849bChris Wilson
The warnings of implicit function declarations were lost amongst the noise. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: Add a modicum of DBG for PolyFillRectChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20Sanity check that the driver is an i915.ko GEM device before claiming itChris Wilson
This fixes an issue with us claiming Poulsbo and friends even though we do not speak their language. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: Avoid migrating the BLT composite src to the GPU if the dst is notChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: Remove unneeded source bo unref after __sna_render_pixmap_bo()Chris Wilson
As __sna_render_pixmap_bo() deliberately does not reference its returned bo, we need to avoid unreferencing it else we cause explosions later. Fixes regression from commit a13781d19defc97af6a279c11a85e33ef825020e Author: Chris Wilson <chris@chris-wilson.co.uk> Date: Sun Aug 19 09:45:12 2012 +0100 sna: Enable BLT composite functions to target CPU buffers Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-20sna: Flush the batch before preparing for a FlushCallbackChris Wilson
As we end up submitting and maybe synchronising upon a batch within FlushCallback (or our client will) it is important that we start that serialized batch as early as possible to minimise the impending stalls. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-19sna: Do not use the GPU to migrate to the CPU whilst wedged!Chris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-19sna: Experiment with flushing the batch prior to rendering to a ShmPixmapChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-19sna: Don't promote a ShmPixmap to GPU for a CopyAreaChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-19sna/gen3: Tidy vbo discardChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-19sna: Tweak is_cpu/is_gpu heuristicsChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-19sna: Discard GPU (and damage) after applying clear on migration to CPUChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-19sna/trapezoids: Accept more operators for maybe-inplaceChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-19sna: Update maybe_inplace to recognise more types of handled pixel formatsChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-19sna: Only submit the batch if flushing a DRI client boChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-19sna: compare the correct trailing dword when skipping identical bitmap linesChris Wilson
Fixes regression in 2.20.4 from commit 85192f00e345830541e3715e211b1f98154bbef4 Author: Chris Wilson <chris@chris-wilson.co.uk> Date: Wed Aug 8 12:11:50 2012 +0100 sna: Ignore trailing bits when comparing lines inside the bitmap Reported-by: Edward Sheldrake <ejsheldrake@gmail.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=53699 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2012-08-19sna: Enable BLT composite functions to target CPU buffersChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-22 16:45:53 +0000