summaryrefslogtreecommitdiff
path: root/shared-core/nouveau_mem.c
AgeCommit message (Expand)AuthorFilesLines
2009-03-09nv50: remove division from nv50_vm_bind_linearBen Skeggs1-15/+13
2009-03-06nouveau: don't try to traverse non-existent listsStuart Bennett1-3/+3
2009-03-06drm/nouveau: make portion of vram as reserved for PRAMIN on all chipsetsBen Skeggs1-4/+1
2009-02-22nv50: leave vm offset 0-512MiB invalidBen Skeggs1-1/+1
2009-02-22nouveau: hide instmem map, force use of {prepare,finish}_accessBen Skeggs1-0/+2
2009-02-20nv50: remove clamp to 512MiB VRAMBen Skeggs1-5/+0
2009-02-20nv50: rework vm handling so we can support >512MiB VRAMBen Skeggs1-84/+167
2009-02-20nouveau: use consistant register access macrosBen Skeggs1-13/+13
2009-02-04nouveau: bring in current mm implementationBen Skeggs1-81/+158
2009-02-04nouveau: bring in new mm api definitions, without the actual mm codeBen Skeggs1-4/+7
2008-07-31Merge commit 'origin/master' into modesetting-gemKristian Høgsberg1-1/+0
2008-07-18nv50: use same dma object for fb/tt accessBen Skeggs1-1/+10
2008-07-18nouveau: interface changes for nv5x 3dBen Skeggs1-3/+68
2008-07-08nouveau: interface changes for nv5x 3dBen Skeggs1-2/+64
2008-07-03nv50: s/FALSE/false && s/TRUE/trueMaarten Maathuis1-1/+1
2008-06-27NV50: use list_head item instead of list_head head to avoid confusionMaarten Maathuis1-1/+1
2008-06-25NV50: i misunderstood NOUVEAU_MEM_INTERNAL, so remove itMaarten Maathuis1-3/+0
2008-06-25NV50: Some cleanup and fixes.Maarten Maathuis1-0/+29
2008-06-25nouveau: allocate drm-use vram buffers from end of vram.Ben Skeggs1-22/+36
2008-06-23nv50: oops, keep VRAM allocations aligned at 64KiB - that's our page size..Ben Skeggs1-1/+4
2008-06-23nv50: use same dma object for fb/tt accessBen Skeggs1-1/+10
2008-06-23nouveau: allocate drm-use vram buffers from end of vram.Ben Skeggs1-22/+36
2008-06-22NV50: Initial import of kernel modesetting.Maarten Maathuis1-0/+11
2008-03-13nv50: force channel vram access through vmBen Skeggs1-0/+78
2008-03-11nouveau: move AGP reset to mem_init_agpStuart Bennett1-0/+28
2008-03-06ttm: make sure userspace can't destroy kernel create memory managersDave Airlie1-3/+3
2008-02-16nouveau: no GART on ia64 either.Stephane Marchesin1-2/+2
2008-01-23nouveau: Fix warning in nouveau_mem.cMaarten Maathuis1-1/+1
2008-01-14nouveau: make mem alloc debug a little more verbose.Stephane Marchesin1-1/+1
2007-11-05drm: remove lots of spurious whitespace.Dave Airlie1-12/+10
2007-11-05nouveau: crappy ttm mm init, disabled for now.Ben Skeggs1-17/+87
2007-11-01nouveau: don't use AGP on PPC. It's a hopeless case.Stephane Marchesin1-0/+2
2007-10-23nouveau: fix IGPStephane Marchesin1-1/+1
2007-10-16nouveau: revert unintended change.Ben Skeggs1-1/+2
2007-10-16nouveau: Handle multiple PFIFO exceptions per irq, cleanup output.Ben Skeggs1-2/+1
2007-10-14nouveau: fix warning.Jeremy Kolb1-1/+1
2007-08-31nouveau: give nv03 the last cut.Stephane Marchesin1-12/+0
2007-08-22nouveau: fix the comment and debug message for PCIGART sizeStephane Marchesin1-3/+3
2007-08-19Check also for Linux, as it's not supported on different OSPatrice Mandin1-1/+1
2007-08-19Function pci_get_bus_and_slot needs 2.6.19 or laterPatrice Mandin1-0/+5
2007-08-17nouveau: Detect memory on NFORCE/NFORCE2 correctly.Ben Skeggs1-10/+33
2007-08-15nouveau: Turn some messages into DRM_DEBUGs..Ben Skeggs1-2/+2
2007-08-06nouveau: Bump PCI GART to 16MBStephane Marchesin1-1/+1
2007-08-06nouveau: Various internal and external API changesBen Skeggs1-5/+3
2007-07-20Replace DRM_IOCTL_ARGS with (dev, data, file_priv) and remove DRM_DEVICE.Eric Anholt1-28/+15
2007-07-20Replace filp in ioctl arguments with drm_file *file_priv.Eric Anholt1-27/+35
2007-07-20Remove DRM_ERR OS macro.Eric Anholt1-9/+9
2007-07-17nouveau: G8x PCIEGARTBen Skeggs1-80/+107
2007-07-16drm: remove drmP.h internal typedefsDave Airlie1-1/+1
2007-07-16drm: detypedef drm.h and fixup all problemsDave Airlie1-5/+5