summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/nouveau/nv50_instmem.c
Commit message (Expand)AuthorAgeFilesLines
* drm/nouveau: will need to specify channel for vm-ful gpuobj allocationsBen Skeggs2011-06-231-2/+3
* drm/nvc0: fix suspend/resume of PGRAPH/PCOPYnBen Skeggs2011-06-231-2/+1
* drm/nouveau: split ramin_lock into two locks, one hardirq safeBen Skeggs2011-04-201-4/+6
* Merge commit '5359533801e3dd3abca5b7d3d985b0b33fd9fe8b' into drm-core-nextDave Airlie2011-03-161-0/+8
|\
| * drm/nv50-nvc0: prevent multiple vm/bar flushes occuring simultanenouslyBen Skeggs2011-03-081-0/+8
* | drm/nouveau: rename nouveau_vram to nouveau_memBen Skeggs2011-02-251-1/+1
* | drm/nouveau: don't munge in drm_mm internalsDaniel Vetter2011-02-231-2/+2
|/
* drm/nvc0: enable protection of system-use-only structures in vmBen Skeggs2011-01-171-2/+5
* drm/nouveau: modify vm to accomodate dual page tables for nvc0Ben Skeggs2010-12-211-9/+7
* drm/nv50: fix a couple of vm init issuesFrancisco Jerez2010-12-161-6/+7
* drm/nouveau: kick vram functions out into an "engine"Ben Skeggs2010-12-081-3/+6
* drm/nouveau: allow gpuobj vinst to be a virtual address when necessaryBen Skeggs2010-12-081-2/+23
* drm/nv50: tidy up PCIEGART implementationBen Skeggs2010-12-081-9/+3
* drm/nv50: implement global channel address space on new VM codeBen Skeggs2010-12-081-34/+14
* drm/nv50: implement BAR1/BAR3 management on top of new VM codeBen Skeggs2010-12-081-149/+109
* drm/nv50: import new vm codeBen Skeggs2010-12-081-9/+3
* drm/nv50: implement custom vram mmBen Skeggs2010-12-081-0/+1
* drm/nouveau: rework gpu-specific instmem interfacesBen Skeggs2010-12-031-57/+73
* drm/nouveau: simplify gpuobj suspend/resumeBen Skeggs2010-12-031-18/+3
* drm/nouveau: pass gpuobj alignment request down into backing allocatorBen Skeggs2010-12-031-5/+5
* drm/nouveau: add more fine-grained locking to channel list + structuresBen Skeggs2010-12-031-7/+7
* drm/nv50: implement possible workaround for NV86 PGRAPH TLB flush hangBen Skeggs2010-11-181-1/+0
* drm/ttm: restructure to allow driver to plug in alternate memory managerBen Skeggs2010-10-051-1/+1
* drm/nv50: flush bar1 vm / dma object setup before poking 0x1708Ben Skeggs2010-09-241-0/+2
* drm/nouveau: Remove implicit argument from nv_wait().Francisco Jerez2010-09-241-3/+3
* drm/nouveau: tidy ram{ht,fc,ro} a bitBen Skeggs2010-09-241-4/+0
* drm/nouveau: rework init ordering so nv50_instmem.c can be less badBen Skeggs2010-09-241-188/+153
* drm/nv50: allow gpuobjs that aren't mapped into apertureBen Skeggs2010-09-241-0/+2
* drm/nouveau: simplify fake gpu objectsBen Skeggs2010-09-241-11/+8
* drm/nouveau: remove nouveau_gpuobj_ref completely, replace with sanityBen Skeggs2010-09-241-69/+57
* drm/nouveau: modify object accessors, offset in bytes rather than dwordsBen Skeggs2010-09-241-4/+6
* drm/nv50: initialize ramht_refs list for faked 0 channelMarcin Slusarz2010-09-031-0/+2
* drm/nv50-nvc0: ramht_size is meant to be in bytes, not entriesBen Skeggs2010-08-171-1/+1
* drm/nv50: correct wait condition for instmem flushBen Skeggs2010-07-261-2/+2
* drm/nv50: use correct PRAMIN flush register on original nv50Ben Skeggs2010-07-261-0/+8
* drm/nv50: move tlb flushing to a helper functionBen Skeggs2010-07-131-13/+10
* drm/nouveau: add instmem flush() hookBen Skeggs2010-07-131-27/+6
* drm/nouveau: use drm_mm in preference to custom code doing the same thingBen Skeggs2010-07-131-7/+5
* drm: Remove drm_resource wrappersJordan Crouse2010-06-011-1/+1
* drm/nv50: fix instmem init on IGPs if stolen mem crosses 4GiB markBen Skeggs2010-04-091-3/+4
* drm/nouveau: detect vram amount once, and save the valueBen Skeggs2010-04-091-7/+2
* drm/nouveau: use ALIGN instead of open coding itMatt Turner2010-02-251-1/+1
* drm/nv50: fix instmem binding on IGPs to point at stolen system memoryBen Skeggs2010-02-231-18/+40
* drm/nouveau: Add DRM driver for NVIDIA GPUsBen Skeggs2009-12-111-0/+509
OpenPOWER on IntegriCloud