summaryrefslogtreecommitdiffstats
path: root/drivers/gpu
Commit message (Expand)AuthorAgeFilesLines
* drm/nv40: make detection of 0x4097-ful chipsets available everywhereBen Skeggs2011-01-173-18/+20
* drm/nouveau: fix hwmon device bindingLucas Stach2011-01-071-2/+1
* drm/nouveau: create grctx on the fly on all chipsetsBen Skeggs2011-01-074-12/+14
* drm/nvc0: fix init without firmware presentBen Skeggs2011-01-061-5/+3
* drm/nvc0/pgraph: fix 0x406028/0x405870 initBen Skeggs2011-01-011-3/+7
* drm/nvc0/pgraph: more unit namesBen Skeggs2010-12-311-6/+6
* drm/nvc0/pfifo: support for chipsets with only one PSUBFIFO (0xc1)Ben Skeggs2010-12-311-6/+12
* drm/nvc0: reserve only subc 0 for kernel useBen Skeggs2010-12-302-9/+15
* drm/nv50: sync up gr data error names with rnn, use for nvc0 alsoBen Skeggs2010-12-303-13/+44
* drm/nvc0: parse a couple more PGRAPH_INTRBen Skeggs2010-12-301-0/+16
* drm/nvc0: nuke left-over debug messagesBen Skeggs2010-12-292-3/+0
* drm/nvc0: kill off a couple more magicsBen Skeggs2010-12-293-19/+21
* drm/nouveau: Validate channel indices passed from userspace.Michel Hermier2010-12-271-0/+3
* drm/nouveau: Only select ACPI_VIDEO if its dependencies are metBen Hutchings2010-12-271-1/+1
* drm/nvc0: accelerate ttm buffer movesBen Skeggs2010-12-211-1/+56
* drm/nvc0: initial support for tiled buffer objectsBen Skeggs2010-12-215-25/+62
* drm/nvc0: implement fbcon accelerationBen Skeggs2010-12-214-6/+300
* drm/nvc0: implement pgraph engine hooksBen Skeggs2010-12-216-3/+3631
* drm/nvc0: implement pfifo engine hooksBen Skeggs2010-12-212-0/+361
* drm/nvc0: implement fencingBen Skeggs2010-12-211-8/+20
* drm/nvc0: fix channel dma init pathsBen Skeggs2010-12-213-10/+38
* drm/nvc0: skip dma object creation for drm channelBen Skeggs2010-12-211-0/+5
* drm/nvc0: implement channel structure initialisationBen Skeggs2010-12-211-4/+20
* drm/nvc0: gpuobj_new need only check validity and init the relevant engineBen Skeggs2010-12-211-4/+11
* drm/nvc0: reject the notifier_alloc ioctlBen Skeggs2010-12-211-0/+5
* drm/nvc0: create shared channel vmBen Skeggs2010-12-211-0/+16
* drm/nvc0: initial vm implementation, use for bar1/bar3 managementBen Skeggs2010-12-218-204/+266
* drm/nvc0: import initial vm backendBen Skeggs2010-12-217-7/+169
* drm/nouveau: modify vm to accomodate dual page tables for nvc0Ben Skeggs2010-12-214-75/+65
* drm/nv50: add missing license header to nv50_fbcon.cBen Skeggs2010-12-211-0/+24
* drm/nv50: fix smatch warning in nv50_vram.cBen Skeggs2010-12-211-1/+2
* drm/nouveau: sizeof() vs ARRAY_SIZE()Dan Carpenter2010-12-211-1/+1
* drm/radeon/kms: properly print ontario chip idAlex Deucher2010-12-161-0/+1
* drm/radeon/kms: fix vram start calculation on ontario (v2)Alex Deucher2010-12-164-13/+8
* Merge remote branch 'nouveau/drm-nouveau-next' of ../drm-nouveau-next into dr...Dave Airlie2010-12-1662-4014/+6599
|\
| * drm/nv50: fix a couple of vm init issuesFrancisco Jerez2010-12-161-6/+7
| * drm/nv04-nv40: Fix up PCI(E) GART DMA object bus address calculation.Francisco Jerez2010-12-083-18/+10
| * drm/nouveau: kick vram functions out into an "engine"Ben Skeggs2010-12-087-51/+74
| * drm/nouveau: allow gpuobj vinst to be a virtual address when necessaryBen Skeggs2010-12-082-2/+24
| * drm/nv50: tidy up PCIEGART implementationBen Skeggs2010-12-085-95/+79
| * drm/nv50: enable non-contig vram allocations where requestedBen Skeggs2010-12-081-1/+5
| * drm/nv50: enable 4KiB pages for small vram allocationsBen Skeggs2010-12-082-19/+25
| * drm/nv50: implement global channel address space on new VM codeBen Skeggs2010-12-0813-216/+86
| * drm/nv50: implement BAR1/BAR3 management on top of new VM codeBen Skeggs2010-12-084-153/+162
| * drm/nv50: import new vm codeBen Skeggs2010-12-0811-22/+714
| * drm/nv50: implement custom vram mmBen Skeggs2010-12-088-122/+650
| * drm/nouveau: Avoid potential race between nouveau_fence_update() and context ...Francisco Jerez2010-12-081-8/+11
| * drm/nouveau: fix use of drm_mm_node in semaphore objectBen Skeggs2010-12-081-3/+2
| * drm/nouveau: wrap calls to ttm_bo_validate()Ben Skeggs2010-12-083-5/+20
| * drm/nouveau: no need to zero dma objects, we fill them completely anywayBen Skeggs2010-12-081-5/+2
OpenPOWER on IntegriCloud