summaryrefslogtreecommitdiff
path: root/libdrm
AgeCommit message (Collapse)Author
2009-10-20intel: Only call clock_gettime once per unreference_final.Eric Anholt
Notably when freeing a batchbuffer, we often end up freeing many of the buffers it points at as well. Avoiding repeated calls brings us a 9% CPU win for cairo-gl. [ # ] backend test min(s) median(s) stddev. count before: [ 0] gl firefox-talos-gfx 58.941 58.966 0.75% 3/3 after: [ 0] gl firefox-talos-gfx 54.186 54.195 0.49% 3/3
2009-10-20intel: Improve bo_references performance by skipping the tree walk.Eric Anholt
If the target we're asking about hasn't ever been used as a relocation target, then it obviously hasn't been used as a target by the batch's reloc tree. This is the common case for good GL programming where you only map fresh buffers, and gives us a 5% win in cairo-gl. [ # ] backend test min(s) median(s) stddev. count before: [ 0] gl firefox-talos-gfx 64.680 64.756 0.06% 3/3 after: [ 0] gl firefox-talos-gfx 60.816 60.970 0.29% 3/3
2009-10-20nouveau: retry if pushbuf ioctl interrupted by signalBen Skeggs
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2009-10-19nouveau: function to return status of bo being referenced in pushbufBen Skeggs
Will be used to implement gallium's is_{texture,buffer}_referenced() callbacks properly. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2009-10-13nouveau: nv30: add render target logbase2 width,heightPatrice Mandin
2009-10-13intel: Fallback to atomic-ops.h [libatomic-ops-dev]Chris Wilson
Use the external implementation for atomic operations across a wide range of architectures. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2009-10-08intel: Remove the asserts about the ignored alignment parameter.Eric Anholt
I slipped it in with the alloc_tiled changes, since we were explicitly throwing the parameter away. It caught some bogus released code, which we've now fixed, so remove the asserts to keep old drivers working.
2009-10-06intel: Add a bo_alloc function for tiled BOs.Jesse Barnes
This simplifies driver code in handling object allocation, and also gives us an opportunity to possibly cache tiled buffers if it turns out to be a win. [anholt: This is chopped out of the execbuf2 patch, as it seems to be useful separately and cleans up the execbuf2 changes to be more obvious]
2009-10-06intel: Fix up some stale doxygen comments.Eric Anholt
2009-10-06intel: Reformat to the kernel coding style. Welcome to the 8-space future.Eric Anholt
This is done with: Lindent *.[ch] perl -pi -e 's|drm_intel_bo \* |drm_intel_bo *|g' *.[ch] perl -pi -e 's|drm_intel_bufmgr \* |drm_intel_bufmgr *|g' *.[ch] perl -pi -e 's|drm_intel_bo_gem \* |drm_intel_bo_gem *|g' *.[ch] perl -pi -e 's|drm_intel_bufmgr_gem \* |drm_intel_bufmgr_gem *|g' *.[ch] perl -pi -e 's|_fake \* |_fake *|g' *.[ch] hand-editing to whack indented comments into line and other touchups.
2009-10-06intel: Don't allocate more relocation entries than the BO could support.Eric Anholt
This saves 32k of relocation entry storage for many 965 state buffers. No noticeable impact on performance for cairo-gl firefox.
2009-10-03intel: Add a configure option to *disable* building libdrm-intelChris Wilson
In conjunction with the atomic operation patch, it may be more convenient for some people to disable building libdrm-intel and its dependencies upon the atomic intrinsics then it is for them to use a supported compiler. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2009-10-03intel: report errnoChris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2009-10-03libdrm_radeon: Zero-initialize structures to silence valgrind warningsNicolai Hähnle
Signed-off-by: Nicolai Hähnle <nhaehnle@gmail.com>
2009-10-02intel: Use atomic refcountersChris Wilson
As the target architecture for Intel GPUs is the x86, we can presume to have reasonable compiler support for Intel atomic intrinsics, i.e. gcc, and so use those in preference to pulling in a complicated mess of fragile assembly. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> [anholt: hand-resolved against my previous commit. This brings cairo-gl firefox-talos-gfx time from 65 seconds back down to 62 seconds.] Signed-off-by: Eric Anholt <eric@anholt.net>
2009-10-02intel: Mark cached bo as purgeableChris Wilson
Set the DONTNEED flag on cached buffers so that the kernel is free to discard those when under memory pressure. [anholt: This takes firefox-talos-gfx time from ~62 seconds to ~65 seconds on my GM965, but it seems like a hit worth taking for the improved functionality from saving memory] Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Eric Anholt <eric@anholt.net>
2009-10-02intel: Don't free the reloc list when putting a freed BO in the cache.Eric Anholt
This takes firefox-talos-gfx from 74 seconds to 70 seconds on my GM965.
2009-10-01intel: Add a new function to check if a BO's reloc tree references some BO.Eric Anholt
There are a bunch of places in GL where if we can't do this we have to flush the batchbuffer, and the cost of lookups here is outweighed by flush savings.
2009-09-21intel: Remove the max_entries stuff that complicated bo reuse.Eric Anholt
I thought I was going to do all sorts of crazy experiments with it. I never did, and it turned out the free-after-a-few-seconds plan is working out fine.
2009-09-21intel: Remove the old swrast flag for reducing cache flushing.Eric Anholt
It hasn't been doing anything effective since 52e5d24fae4af6f2f4a5304a516c8c5ab347a11b, and we pretty much don't bo_map pinned buffers any more anyway.
2009-09-17drmModeFreeConnector: free encoders and propertiesKeith Packard
These were leaking. Signed-off-by: Keith Packard <keithp@keithp.com>
2009-09-15radeon: fix 32/64 bit issue with sign extensionDave Airlie
Not sure what intptr_t was up to here. Reported and tested by: Kevin DeKorte Signed-off-by: Dave Airlie <airlied@redhat.com>
2009-09-07libdrm_intel: include B43 chipset checkZhenyu Wang
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
2009-09-04libdrm_intel: add new pci idsZhenyu Wang
New ids for G41, Clarkdale and Arrandale. Make sure we don't need to count fence also on new chips. Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
2009-08-28Add drm_intel_bo_busy to query whether mapping a BO would block.Eric Anholt
2009-08-28Revert "libdrm_radeon: Always wait for BO idle in bo_map."Michel Dänzer
This reverts commit 0a732983f059c353b267b6bf877e1f0eea4e033f. Paul Nieminen and Dave Airlie pointed out on IRC that this shouldn't be necessary. I was seeing visual corruption in X before I made this change, but I can't reproduce that anymore so it was probably an unrelated issue.
2009-08-27libdrm_radeon: Always wait for BO idle in bo_map.Michel Dänzer
This allows users to eliminate explicit bo_wait calls before bo_map calls.
2009-08-22radeon: add support for busy/domain check interface.Pauli Nieminen
airlied: modified the interface to drop busy return value, just return it normally, also fixed int->uint32_t for domain Signed-off-by: Pauli Nieminen <suokkos@gmail.com>
2009-08-19nouveau: fix a thinko in copyless pushbuf ioctlBen Skeggs
No idea why G80 doesn't hit this, but, this fixes at least one NV40 card.
2009-08-18libdrm_radeon: Optimize copy of table to cs buffer with specialized call.Pauli Nieminen
Using this call in OUT_BATCH_TABLE reduces radeonEmitState cpu usage from 9% to 5% and emit_vpu goes from 7% to 1.5%. I did use calgrind to profile gears for cpu hotspots with r500 card. Signed-off-by: Pauli Nieminen <suokkos@gmail.com>
2009-08-18libdrm_radeon: Fix loops so that compiler can optimize them.Pauli Nieminen
GCC did war about optimization not possible because possible forever loop. Signed-off-by: Pauli Nieminen <suokkos@gmail.com>
2009-08-18libdrm/radeon: Update head of linked list not to point freed memory.Pauli Nieminen
Signed-off-by: Pauli Nieminen <suokkos@gmail.com>
2009-08-18nouveau: support for copy-less pushbuf ioctlBen Skeggs
2009-08-18nouveau: for the moment, assert if we exceed some reloc limitsBen Skeggs
Nasty, but nicer than silently not writing into the pushbuf
2009-08-17radeon: fix bo wait at map time.Dave Airlie
2009-08-15radeon: fix GTT writing space checkDave Airlie
Noticed by vehemens on irc. Signed-off-by: Dave Airlie <airlied@redhat.com>
2009-08-05link libdrm_intel with -lrt for new use of clock_gettime().Anssi Hannula
Signed-off-by: Eric Anholt <eric@anholt.net>
2009-08-01libdrm_radeon: add tiling supportDave Airlie
2009-08-01radeon: don't map/unmap explicitly.Dave Airlie
This caches the mapping and just use mapping as a sync point
2009-07-28nouveau: don't overwrite user-specified bo size needlesslyBen Skeggs
2009-07-28nouveau: user buffers need to be mappableBen Skeggs
2009-07-28nouveau: drm api 0.0.15, update object header, remove fake bo supportBen Skeggs
2009-07-27libdrm/nouveau: unmap before ufree means nvbo->sysmem != NULL, which ↵Maarten Maathuis
inbalances cpu_prep/cpu_finish - The bo was mapped with sysmem == NULL, so this means cpu prep is called. - The bo was unmapped with sysmem != NULL, so this means cpu finish is not called. - This can lead to a non-zero "cpu writers" count in ttm_bo.
2009-07-09intel: Free buffers in the BO cache that haven't been reused in a while.Eric Anholt
The goal of the BO cache is to keep buffers on hand for fast continuous use, as in every frame of a game or every batchbuffer of the X Server. Keeping older buffers on hand not only doesn't serve this purpose, it may hurt performance by resulting in disk cache getting kicked out, or even driving the system to swap. Bug #20766.
2009-07-09nouveau: fix pin for buffers created with bo_wrapBen Skeggs
2009-07-06libdrm: Make chown check for return valuePauli Nieminen
If call was interrupted by signal we have to make call again. Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
2009-07-06intel: Fix up math errors when allocating very large BOs.Eric Anholt
The logbase2 would overflow and wrap the size around to 0, making the code allocate a 4kb object instead. By simplifying the code to just walk the 14-entry bucket array comparing sizes instead of indexing on ffs(1 << logbase2(size)), we avoid silly math errors and have code of approximately the same speed. Many thanks to Simon Farnsworth for debugging and providing a working patch. Bug #27365.
2009-07-06intel: fix compiler warning about returning a void value.Edward O'Callaghan
bug #21999
2009-07-06libdrm: Fix pci id numbers to unsigned so code won't mix signed/unsigned ↵Pauli Nieminen
integers.
2009-07-06strcasecmp is in strings.h.Ian Romanick
Based on patch by Pauli Nieminen. Thanks.