Age | Commit message (Collapse) | Author | |
---|---|---|---|
2007-02-15 | Initial support for fence object classes. | Thomas Hellstrom | |
(Fence objects belonging to different command submission mechanisms). | |||
2007-02-15 | Fix build against older kernels. | Michel Dänzer | |
2007-02-14 | Merge branch 'ttm-vram-0-1-branch' | Thomas Hellstrom | |
2007-02-14 | Fix multiple spinlock unlocking | Thomas Hellstrom | |
2007-02-14 | Rename drm_ttm.h to drm_objects.h | Thomas Hellstrom | |
Fix up some header incompatibilities in drm_fence.c caused by the previous commit. | |||
2007-02-14 | Move fence- and buffer-object related header stuff to drm_ttm.h | Thomas Hellstrom | |
2007-02-14 | Remove an intel-specific hack and replace it with a fence driver callback. | Thomas Hellstrom | |
2007-02-14 | Set the drm bus map type for each buffer object memory type. | Thomas Hellstrom | |
2007-02-14 | Rework buffer object vm code to use nopfn() for kernels >= 2.6.19. | Thomas Hellstrom | |
2007-02-13 | Remove debug printout. | Thomas Hellstrom | |
2007-02-13 | Bugzilla Bug #9457 | Thomas Hellstrom | |
Add refcounting of user waiters to the DRM hardware lock, so that we can use the DRM_LOCK_CONT flag more conservatively. Also add a kernel waiter refcount that if nonzero transfers the lock for the kernel context, when it is released. This is useful when waiting for idle and can be used for very simple fence object driver implementations for the new memory manager. It also resolves the AIGLX startup deadlock for the sis and the via drivers. i810, i830 still require that the hardware lock is really taken so the deadlock remains for those two. I'm not sure about ffb. Anyone familiar with that code? | |||
2007-02-13 | More bugfixes. | Thomas Hellstrom | |
Fixed memory, pinned buffers and unmappable memory now seems fully functional. | |||
2007-02-12 | Fix some outdated URLs, remove others. | Adam Jackson | |
2007-02-12 | Lindent. | Thomas Hellstrom | |
2007-02-12 | More bugfixes. | Thomas Hellstrom | |
2007-02-12 | Cleanup and fix support for pinned buffers. | Thomas Hellstrom | |
2007-02-10 | Various bugfixes. | Thomas Hellstrom | |
2007-02-09 | I915 accelerated blit copy functional. | Thomas Hellstrom | |
Fixed - to System memory copies are implemented by flipping in a cache-coherent TTM, blitting to it, and then flipping it out. | |||
2007-02-09 | Reinstate some LRU handling. | Thomas Hellstrom | |
2007-02-09 | Remove some code that should have gone in | Thomas Hellstrom | |
commit 6a49d9a8abd9f168211017c2d585d0d64e89c530 | |||
2007-02-09 | Fix copyright statements. | Thomas Hellstrom | |
2007-02-09 | Fix evict_mutex locking range. | Thomas Hellstrom | |
Implement unmappable buffers. (fault moves them to mappable when needed). Various bugfixes. | |||
2007-02-08 | Add an accelerated buffer copy cleanup helper. | Thomas Hellstrom | |
Export helper functions and make some important buffer-object functions non-static. Add an i915 accelerated blit buffer move for pci memory buffers. | |||
2007-02-08 | Don't create a ttm just to copy from. | Thomas Hellstrom | |
2007-02-08 | Fix mm_block leak. | Thomas Hellstrom | |
Some other minor fixes. | |||
2007-02-08 | A minor function interface change and some memcpy bugfixing. | Thomas Hellstrom | |
Hooray!! it sort of works with a fixed AGP area as faked VRAM. | |||
2007-02-08 | Simplify external ttm page allocation. | Thomas Hellstrom | |
Implement a memcpy fallback for copying between buffers. | |||
2007-02-08 | Update memory compatibility tests. | Thomas Hellstrom | |
Now only pinned buffers are broken. | |||
2007-02-07 | Checkpoint commit. | Thomas Hellstrom | |
Flag handling and memory type selection cleanup. glxgears won't start. | |||
2007-02-07 | Fix a stray unlock_kernel() in drm_vm.c | Thomas Hellstrom | |
Add a file for memory move helpers, drm_bo_move.c Implement generic memory move. Cached, no_move and unmapped memory temporarily broken. | |||
2007-02-06 | Simplify pci map vs no pci map choice. | Thomas Hellstrom | |
2007-02-06 | Implement a drm_mem_reg_t substructure in the buffer object type. | Thomas Hellstrom | |
2007-02-06 | Implement a policy for selecting memory types. | Thomas Hellstrom | |
2007-02-05 | i915: Add copy-blit operation. | Thomas Hellstrom | |
2007-02-03 | nouveau: add missing nv04_graph.c symlink. | Stephane Marchesin | |
2007-02-03 | nouveau: fix nv04 graph routines for new register names. | Stephane Marchesin | |
2007-02-02 | Make also later kernels work with buffer object vm | Thomas Hellstrom | |
and clean up some function names. | |||
2007-02-02 | Make vm handle buffer objects instead of ttm objects. | Thomas Hellstrom | |
Remove ttm objects. Make vm aware of PCI memory type buffer objects. (Only works for pre 2.6.16 kernels for now). | |||
2007-02-01 | Fix missing ttm_open_vma call from previous commit. | Thomas Hellstrom | |
Honour the ttm backend cant-use-aperture flag. | |||
2007-02-01 | Prepare for removal of the ttm_object type. | Thomas Hellstrom | |
2007-02-01 | Protect drm_mmap against disappearing maps. | Thomas Hellstrom | |
The map lists and hash tables are protected using dev->struct_mutex, but drm_mmap strangely never locked this mutex. | |||
2007-01-31 | memory manager: Make device driver aware of different memory types. | Thomas Hellstrom | |
Memory types are either fixed (on-card or pre-bound AGP) or not fixed (dynamically bound) to an aperture. They also carry information about: 1) Whether they can be mapped cached. 2) Whether they are at all mappable. 3) Whether they need an ioremap to be accessible from kernel space. In this way VRAM memory and, for example, pre-bound AGP appear identical to the memory manager. This also makes support for unmappable VRAM simple to implement. | |||
2007-01-31 | Fix an error-path oops. | Thomas Hellstrom | |
2007-01-30 | Add a buffer object transfer function. | Thomas Hellstrom | |
Creates a placeholder for the old buffer contents when it is transfered to / from static memory like VRAM. | |||
2007-01-30 | Clean up buffer object destruction somewhat. | Thomas Hellstrom | |
2007-01-29 | Use pre-defined list_splice function. | Thomas Hellstrom | |
2007-01-29 | s/buf/bo/ for consistency. | Thomas Hellstrom | |
2007-01-29 | Some cleanup. A buffer object should only have one active memory type. | Thomas Hellstrom | |
2007-01-25 | Remove a scary error printed when we were leaking memory caches. | Thomas Hellstrom | |
We don't use memory caches anymore... Fix memory accounting initialization to only use low or DMA32 memory. | |||
2007-01-13 | nouveau: nv20 graph ctx switch. | Matthieu Castet | |
Untested... |