summaryrefslogtreecommitdiff
path: root/linux-core/i915_buffer.c
AgeCommit message (Collapse)Author
2008-04-06[I915] Fix VRAM eviction.Thomas Hellstrom
2008-01-17i915: fix invalid opcode exception on cpus without clflushKyle McMartin
i915_flush_ttm was unconditionally executing a clflush instruction to (obviously) flush the cache. Instead, check if the cpu supports clflush, and if not, fall back to calling wbinvd to flush the entire cache. Signed-off-by: Kyle McMartin <kmcmartin@redhat.com>
2007-12-21Rename inappropriately named 'mask' fields to 'proposed_flags' instead.Keith Packard
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.
2007-11-29drm: more cleanupsDave Airlie
2007-11-06i915: cleanup most of the whitespaceDave Airlie
2007-11-05drm: remove lots of spurious whitespace.Dave Airlie
Kernel "cleanfile" script run.
2007-10-30drm/i915: add driver cache flush entry pointDave Airlie
Use clflush on Intel hardware to flush cached objects.
2007-10-21Disable i915 accelerated blit copy moves for now until we canThomas Hellstrom
guarantee that it doesn't clash with the X server.
2007-10-12i915: check mask instead of flags for buffer fence typesDave Airlie
2007-09-22Add fence error member.Thomas Hellstrom
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.
2007-07-16drm: detypedef ttm/bo/fence codeDave Airlie
2007-07-16drm: remove drmP.h internal typedefsDave Airlie
2007-06-12Try to make buffer object / fence object ioctl args 64-bit safe.Thomas Hellstrom
Introduce tile members for future tiled buffer support. Allow user-space to explicitly define a fence-class. Remove the implicit fence-class mechanism. 64-bit wide buffer object flag member.
2007-04-18Simplify the ttm backend interface and the agp ttm backend.Thomas Hellstrom
2007-02-16Simple fence object sample driver for via, based on idling the GPU.Thomas Hellstrom
Buffer object driver for via. Some changes to buffer object driver callbacks. Improve fence flushing.
2007-02-15Initial support for fence object classes.Thomas Hellstrom
(Fence objects belonging to different command submission mechanisms).
2007-02-14Set the drm bus map type for each buffer object memory type.Thomas Hellstrom
2007-02-13More bugfixes.Thomas Hellstrom
Fixed memory, pinned buffers and unmappable memory now seems fully functional.
2007-02-12Lindent.Thomas Hellstrom
2007-02-12Cleanup and fix support for pinned buffers.Thomas Hellstrom
2007-02-10Various bugfixes.Thomas Hellstrom
2007-02-09I915 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.
2007-02-08Add 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.
2007-02-07Checkpoint commit.Thomas Hellstrom
Flag handling and memory type selection cleanup. glxgears won't start.
2007-02-06Simplify pci map vs no pci map choice.Thomas Hellstrom
2007-02-06Implement a policy for selecting memory types.Thomas Hellstrom
2007-02-05i915: Add copy-blit operation.Thomas Hellstrom
2007-02-02Make 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).
2007-01-31memory 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.
2006-10-18Avoid driver-specific AGP user-populated types, since we don't know what AGPThomas Hellstrom
driver we're on. Avoid global cache flushes before inserting pages. In general, they are never mapped, and not accessed through the kernel map, so a cache flush should not be necessary. The exception is pages that are bound cached. We might need a cache flush for those.
2006-10-17Lindent.Thomas Hellstrom
2006-10-16Change Intel AGP memory type numbers.Thomas Hellstrom
2006-10-12Simplify the AGP backend interface somewhat.Thomas Hellstrom
Fix buffer bound caching policy changing, Allow on-the-fly changing of caching policy on bound buffers if the hardware supports it. Allow drivers to use driver-specific AGP memory types for TTM AGP pages. Will make AGP drivers much easier to migrate.
2006-09-26Allow for a driver to overload the ttm backend object methods.Thomas Hellstrom
2006-09-12Use lazy fence wait when possible even for RW fences. Saves some CPU.Thomas Hellstrom
Lindent.
2006-09-01Various bugfixes.Thomas Hellstrom
2006-08-31Validation and fencing.Thomas Hellstrom
2006-08-22Initial i915 buffer object driverThomas Hellstrom