| Age | Commit message (Collapse) | Author |
|---|
|
|
|
This makes an allocated block actually align itself and returns any
wasted space to the manager.
Also add some functions to grow and shrink the managed area.
This will be used in the future to manage the buffer object swap cache.
|
|
|
|
|
|
otherwise data will be missing, which becomes apparent when the kernel evicts
batch buffers which are likely to be written into in the evicted state,
and then rebound to the AGP aperture.
This means we cannot rely on the AGP module to flush the
cache for us.
|
|
|
|
|
|
|
|
|
|
|
|
Fix some refcounting errors.
Fix some error messages.
|
|
Conflicts:
linux-core/drmP.h
linux-core/drm_drv.c
linux-core/drm_irq.c
linux-core/drm_stub.c
shared-core/drm.h
shared-core/i915_drv.h
shared-core/i915_irq.c
|
|
|
|
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.
|
|
|
|
that is now handled by the memory accounting.
|
|
|
|
Use byte unit for /proc printout of memory usage for small sizes to be
able to detect memory allocation bugs more easily.
|
|
|
|
The mm_lock function is used when leaving vt. It evicts _all_ buffers.
Buffers with the DRM_BO_NO_MOVE attribute set will be guaranteed to
get the same offset when / if they are rebound.
|
|
makes the client code a lot cleaner. Prepare buffer manager for lock and
unlock calls.
|
|
Fix up init and destruction code.
|
|
bug 8662
|
|
|
|
|
|
|
|
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.
|
|
it will go away in the mainstream kernel.
Some bugfixes, mainly in error paths.
|
|
Adapt for new functions in the 2.6.19 kernel.
Remove the ability to have multiple regions in one TTM.
This simplifies a lot of code.
Remove the ability to access TTMs from user space.
We don't need it anymore without ttm regions.
Don't change caching policy for evicted buffers. Instead change it only
when the buffer is accessed by the CPU (on the first page fault).
This tremendously speeds up eviction rates.
Current code is safe for kernels <= 2.6.14.
Should also be OK with 2.6.19 and above.
|
|
|
|
r100/r200 as others might be unsafe (r300 already does this), and add checking for these we need but aren't safe. Check the RADEON_CP_INDX_BUFFER packet on both r200 and r300 as it isn't safe neither.
|
|
|
|
mach64_state.c: convert the DRM_MACH64_BLIT ioctl to submit a pointer to
user-space memory rather than a DMA buffer index, similar to DRM_MACH64_VERTEX.
This change allows the DDX to map the DMA buffers read-only and eliminate a
security problem where a client can alter the contents of the DMA buffer after
submission to the DRM.
This change also affects the DRI/DRM interface. Performace-wise, it basically
affects PCI mode where I get a ~12% speedup for some Mesa demos I tested.
This is mainly due to eliminating an ioctl for allocating the DMA buffer.
mach64_dma.c: move the responsibility for allocating memory for the DMA ring
in PCI mode to the DDX.
This change affects the DDX/DRM interface and unifies a couple of PCI/AGP code
paths for ring memory in the DRM.
Bump the mach64 DRM version major and date.
|
|
Add DRM_PCI_BUFFER_RO flag for mapping PCI DMA buffer read-only. An additional
flag is needed, since PCI DMA buffers do not have an associated map.
|
|
Factor out from mach64_dma_dispatch_vertex() the code to reclaim an unsed
buffer, in preperation for using it in mach64_dma_dispatch_blit() also.
|
|
Factor out from mach64_freelist_get() the code to reclaim a completed buffer,
this is to improve readability for me.
|
|
Map the DMA buffers from the same linear address as the vertex bufs. If
dev->agp_buffer_token is not set, mach64 drm maps the DMA buffers from
linear address 0x0.
|
|
(cherry picked from f6238cf6244b32bd84e3d2819963d7f5473867c8 commit)
|
|
|
|
starting at 0x00100000000. This will hopefully allow us to use
unmap_mapping_range(). Note that user-space will need
64-bit file offset support.
|
|
|
|
|
|
|
|
use drm_reclaim_buffers_locked().
|
|
(cherry picked from d58389968124191a546a14b42ef84edc224be23d commit)
|
|
Initialize the spinlock unconditionally when struct drm_device is filled in,
and return early in drm_locked_tasklet() if the driver doesn't support IRQs.
|
|
|
|
|
|
This fixes issues on X server startup with versions of xf86-video-intel that
enable the IRQ before they have a context ID.
(cherry picked from 7af93dd9849442270ec89cb4bbeef5bfd4f9e424 commit)
|
|
Some other minor changes in preparation for actually disabling user interrupts.
|
