Age | Commit message (Collapse) | Author | Files | Lines | |
---|---|---|---|---|---|
2009-09-16 | Merge commit 'origin/kms-pageflip' into vblank-eventvblank-event | Jesse Barnes | 4 | -18/+74 | |
Conflicts: libdrm/xf86drm.h shared-core/drm.h tests/modetest/modetest.c | |||||
2009-09-16 | Merge branch 'kms-pageflip' into vblank-event | Jesse Barnes | 5 | -8/+168 | |
Conflicts: libdrm/xf86drmMode.c shared-core/drm.h tests/modetest/modetest.c | |||||
2009-09-11 | Add support for vblank event | Kristian Høgsberg | 4 | -1/+92 | |
2009-09-07 | libdrm_intel: include B43 chipset check | Zhenyu Wang | 1 | -1/+4 | |
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com> | |||||
2009-09-04 | libdrm_intel: add new pci ids | Zhenyu Wang | 1 | -1/+4 | |
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> | |||||
2009-08-28 | Bump to version 2.4.13 for release.libdrm-2.4.13 | Eric Anholt | 1 | -1/+1 | |
2009-08-28 | Add drm_intel_bo_busy to query whether mapping a BO would block. | Eric Anholt | 4 | -10/+34 | |
2009-08-28 | Revert "libdrm_radeon: Always wait for BO idle in bo_map." | Michel Dänzer | 1 | -1/+4 | |
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. | |||||
2009-08-27 | libdrm_radeon: Always wait for BO idle in bo_map. | Michel Dänzer | 1 | -4/+1 | |
This allows users to eliminate explicit bo_wait calls before bo_map calls. | |||||
2009-08-25 | Kill last remnant of replacefb ioctl | Jakob Bornecrantz | 1 | -1/+0 | |
Kenrels doesn't expose this ioctl | |||||
2009-08-24 | radeon: pull in z pipe changes from kernel | Alex Deucher | 1 | -0/+2 | |
2009-08-22 | radeon: add support for busy/domain check interface. | Pauli Nieminen | 3 | -1/+31 | |
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> | |||||
2009-08-19 | nouveau: fix a thinko in copyless pushbuf ioctl | Ben Skeggs | 1 | -0/+2 | |
No idea why G80 doesn't hit this, but, this fixes at least one NV40 card. | |||||
2009-08-18 | libdrm_radeon: Optimize copy of table to cs buffer with specialized call. | Pauli Nieminen | 1 | -0/+9 | |
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> | |||||
2009-08-18 | libdrm_radeon: Fix loops so that compiler can optimize them. | Pauli Nieminen | 1 | -6/+6 | |
GCC did war about optimization not possible because possible forever loop. Signed-off-by: Pauli Nieminen <suokkos@gmail.com> | |||||
2009-08-18 | libdrm/radeon: Update head of linked list not to point freed memory. | Pauli Nieminen | 1 | -0/+1 | |
Signed-off-by: Pauli Nieminen <suokkos@gmail.com> | |||||
2009-08-18 | nouveau: support for copy-less pushbuf ioctl | Ben Skeggs | 3 | -16/+143 | |
2009-08-18 | nouveau: for the moment, assert if we exceed some reloc limits | Ben Skeggs | 1 | -2/+8 | |
Nasty, but nicer than silently not writing into the pushbuf | |||||
2009-08-17 | radeon: fix bo wait at map time. | Dave Airlie | 1 | -6/+6 | |
2009-08-16 | Filter radeon pkgconfig file as do intel and nouveau | Christoph Brill | 1 | -0/+1 | |
2009-08-15 | radeon: fix GTT writing space check | Dave Airlie | 1 | -1/+1 | |
Noticed by vehemens on irc. Signed-off-by: Dave Airlie <airlied@redhat.com> | |||||
2009-08-05 | link libdrm_intel with -lrt for new use of clock_gettime(). | Anssi Hannula | 1 | -1/+1 | |
Signed-off-by: Eric Anholt <eric@anholt.net> | |||||
2009-08-01 | libdrm_radeon: add tiling support | Dave Airlie | 3 | -15/+92 | |
2009-08-01 | radeon: don't map/unmap explicitly. | Dave Airlie | 1 | -5/+14 | |
This caches the mapping and just use mapping as a sync point | |||||
2009-07-28 | nouveau: don't overwrite user-specified bo size needlessly | Ben Skeggs | 1 | -1/+2 | |
2009-07-28 | nouveau: user buffers need to be mappable | Ben Skeggs | 1 | -1/+1 | |
2009-07-28 | nouveau: drm api 0.0.15, update object header, remove fake bo support | Ben Skeggs | 14 | -1390/+524 | |
2009-07-27 | libdrm/nouveau: unmap before ufree means nvbo->sysmem != NULL, which ↵ | Maarten Maathuis | 1 | -1/+1 | |
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. | |||||
2009-07-15 | Add RADEON_INIT_R600_CP too | Alex Deucher | 1 | -1/+2 | |
this rounds out the r6xx/r7xx stuff in radeon_drm.h | |||||
2009-07-15 | Add R600_SCRATCH_REG_OFFSET to radeon_drm.h | Alex Deucher | 1 | -0/+1 | |
This lets us libdrm from master for r6xx/r7xx 3d | |||||
2009-07-15 | Bump to version 2.4.12 for release.libdrm-2.4.12 | Eric Anholt | 1 | -1/+1 | |
2009-07-09 | intel: Free buffers in the BO cache that haven't been reused in a while. | Eric Anholt | 1 | -1/+33 | |
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. | |||||
2009-07-10 | configure: move AC_USE_SYSTEM_EXTENSIONS up higher | Dave Airlie | 1 | -1/+1 | |
this was giving me a warning on automake 1.11 | |||||
2009-07-09 | nouveau: fix pin for buffers created with bo_wrap | Ben Skeggs | 1 | -1/+3 | |
2009-07-06 | s/AC_USE_SYSTEM_MACROS/AC_USE_SYSTEM_EXTENSIONS/ | Ian Romanick | 1 | -1/+1 | |
Not sure what I was thinking. | |||||
2009-07-06 | libdrm: Make chown check for return value | Pauli Nieminen | 1 | -3/+33 | |
If call was interrupted by signal we have to make call again. Reviewed-by: Ian Romanick <ian.d.romanick@intel.com> | |||||
2009-07-06 | libdrm: Set _XOPEN_SOURCE and _GNU_SOURCE | Ian Romanick | 1 | -2/+2 | |
Several POSIX extensions are used in the libdrm code (e.g., mknod and ffs). Set _XOPEN_SOURCE and _GNU_SOURCE to something reasonable to ensure that prototypes for these functions are available. This is done in configure.ac using AC_USE_SYSTEM_MACROS. This requires autoconf 2.60 or later. Eventually the code should check for the existance of these defines and do something reasonable if they are not available. Inspired by a patch by Pauli Nieminen and suggestions from Julien Cristau. Thanks. Signed-off-by: Ian Romanick <ian.d.romanick@intel.com> | |||||
2009-07-06 | intel: Fix up math errors when allocating very large BOs. | Eric Anholt | 1 | -31/+15 | |
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. | |||||
2009-07-06 | intel: fix compiler warning about returning a void value. | Edward O'Callaghan | 1 | -1/+1 | |
bug #21999 | |||||
2009-07-06 | libdrm: Fix pci id numbers to unsigned so code won't mix signed/unsigned ↵ | Pauli Nieminen | 1 | -6/+6 | |
integers. | |||||
2009-07-06 | strcasecmp is in strings.h. | Ian Romanick | 1 | -0/+1 | |
Based on patch by Pauli Nieminen. Thanks. | |||||
2009-07-06 | libdrm: Remove typedef for non-existing enum | Pauli Nieminen | 1 | -1/+0 | |
2009-07-06 | radeon: move cs space checking code to libdrm_radeon. | Dave Airlie | 6 | -108/+288 | |
This ports a lot of the space checking code into a the common library, so that the DDX and mesa can use it. | |||||
2009-07-03 | radeon: fix cs buffer realloc padding | Jerome Glisse | 1 | -2/+1 | |
We always realloc at least 0x1000 dwords (page on most system) when growing the cs buffer this is to avoid having to realloc at each cs_begin. | |||||
2009-07-03 | radeon: fix realloc of packets. | Dave Airlie | 1 | -1/+1 | |
This should use ndw not cdw, using cdw leads to realloc alignment going wrong | |||||
2009-07-02 | radeon: add buffer naming function | Dave Airlie | 2 | -0/+16 | |
2009-06-30 | radeon: add support for write followed by read relocs. | Dave Airlie | 1 | -5/+12 | |
the DDX does this and used to handle it internally | |||||
2009-06-23 | remove some old ttm bits | Dave Airlie | 1 | -52/+0 | |
2009-06-22 | drm: Strip old ttm. | Thomas Hellstrom | 27 | -7497/+4 | |
Signed-off-by: Thomas Hellstrom <thellstrom-at-vmware-dot-com> | |||||
2009-06-22 | modetest: use gtt unmap for object | Jesse Barnes | 1 | -1/+1 | |
Match gtt map/unmap for correctness. |