| Age | Commit message (Collapse) | Author |
|---|
|
Move unfenced checking into idle checking.
Never time out while waiting for software events like unmapped or unfenced.
|
|
|
|
PCI- or high memory.
This is substantially more efficient than drm_bo_kmap,
since the mapping only lives on a single processor.
Unmapping is done use kunmap_atomic(). Flushes only a single tlb() entry.
Add a support utility int drm_bo_pfn_prot() that returns the
pfn and desired page protection for a given bo offset.
This is all intended for relocations in bound TTMS or vram.
Mapping-accessing-unmapping must be atomic, either using preempt_xx() macros
or a spinlock.
|
|
Flags pending validation were stored in a misleadingly named field, 'mask'.
As 'mask' is already used to indicate pieces of a flags field which are
changing, it seems better to use a name reflecting the actual purpose of
this field. I chose 'proposed_flags' as they may not actually end up in
'flags', and in an case will be modified when they are moved over.
This affects the API, but not ABI of the user-mode interface.
|
|
Aside from changing drm_bind_ttm to drm_ttm_bind, this patch
adds only documentation and fixes the functions inside drm_ttm.c
to all be prefixed with drm_ttm_.
|
|
Creating a ttm was done with drm_ttm_init while destruction was done with
drm_destroy_ttm. Renaming these to drm_ttm_create and drm_ttm_destroy makes
their use clearer. Passing page_flags to the create function will allow that
to know whether user or kernel pages are needed, with the goal of allowing
kernel ttms to be saved for later reuse.
|
|
|
|
|
|
Kernel "cleanfile" script run.
|
|
don't mask off the high dword.
Signed-off-by: Thomas Hellstrom <thomas-at-tungstengraphics-dot-com>
|
|
Also no need to do pre-populate work on single page
|
|
Modify the TTM backend bind arguments.
Export a number of functions needed for driver-specific super-ioctls.
Add a function to map buffer objects from the kernel, regardless of where they're
currently placed.
A number of error fixes.
|
|
|
|
|
|
|
|
Buffer object dereference cleanup.
Add a struct drm_device member to fence objects:
This can simplify code, particularly in drivers.
|
|
(Fence objects belonging to different command submission mechanisms).
|
|
Fixed memory, pinned buffers and unmappable memory now seems
fully functional.
|
|
|
|
|
|
|
|
|
|
Fixed - to System memory copies are implemented by
flipping in a cache-coherent TTM,
blitting to it, and then flipping it out.
|
|
|
|
Implement unmappable buffers. (fault moves them to mappable when needed).
Various bugfixes.
|
|
Export helper functions and make some important buffer-object functions non-static.
Add an i915 accelerated blit buffer move for pci memory buffers.
|
|
|
|
Some other minor fixes.
|
|
Hooray!! it sort of works with a fixed AGP area as faked VRAM.
|
|
Implement a memcpy fallback for copying between buffers.
|
|
Flag handling and memory type selection cleanup.
glxgears won't start.
|
|
Add a file for memory move helpers, drm_bo_move.c
Implement generic memory move.
Cached, no_move and unmapped memory temporarily broken.
|
