 Daniel Vetter
|
e244a443bf
drm/i915: merge shmem_pwrite slow&fast-path
|
13 years ago |
 Chris Wilson
|
dabdfe021a
drm/i915: Avoid using mappable space for relocation processing through the CPU
|
13 years ago |
|
Daniel Vetter
|
644ec02b5d
drm/i915: s/i915_gem_do_init/i915_gem_init_global_gtt
|
13 years ago |
|
Chris Wilson
|
a14917eeb2
drm/i915: Release the mmap offset when purging a buffer
|
13 years ago |
 Ben Widawsky
|
eb2c0c818a
drm/i915: [dinq] shut up two instances -Wunitialized
|
13 years ago |
|
Daniel Vetter
|
0ebb982993
drm/i915: enable lazy global-gtt binding
|
13 years ago |
|
Daniel Vetter
|
74898d7edc
drm/i915: bind objects to the global gtt only when needed
|
13 years ago |
|
Daniel Vetter
|
741639079c
drm/i915: split out dma mapping from global gtt bind/unbind functions
|
13 years ago |
|
Chris Wilson
|
c501ae7f33
drm/i915: Only clear the GPU domains upon a successful finish
|
13 years ago |
|
Chris Wilson
|
eadb29a9c5
drm/i915: Silence the error message from i915_wait_request()
|
13 years ago |
|
Chris Wilson
|
a71d8d9452
drm/i915: Record the tail at each request and use it to estimate the head
|
13 years ago |
|
Daniel Vetter
|
53d227f282
drm/i915: fixup seqno allocation logic for lazy_request
|
13 years ago |
|
Daniel Vetter
|
5391d0cffe
drm/i915: outstanding_lazy_request is a u32
|
13 years ago |
|
Daniel Vetter
|
e21af88d39
drm/i915: enable ppgtt
|
13 years ago |
|
Daniel Vetter
|
7bddb01fb9
drm/i915: ppgtt binding/unbinding support
|
13 years ago |
|
Daniel Vetter
|
11782b0233
drm/i915: consolidate swizzling control bit frobbing
|
13 years ago |
|
Daniel Vetter
|
f691e2f4ce
drm/i915: swizzling support for snb/ivb
|
13 years ago |
|
Daniel Vetter
|
8461d22677
drm/i915: rewrite shmem_pread_slow to use copy_to_user
|
13 years ago |
|
Daniel Vetter
|
8c59967c44
drm/i915: rewrite shmem_pwrite_slow to use copy_from_user
|
13 years ago |
|
Daniel Vetter
|
5c0480f21f
drm/i915: fall through pwrite_gtt_slow to the shmem slow path
|
13 years ago |
|
Chris Wilson
|
068c6ff1cb
drm/i915: Remove the upper limit on the bo size for mapping into the CPU domain
|
13 years ago |
|
Daniel Vetter
|
39965b3766
drm/i915: don't trash the gtt when running out of fences
|
13 years ago |
|
Chris Wilson
|
1690e1eb7a
drm/i915: Separate fence pin counting from normal bind pin counting
|
13 years ago |
|
Ben Widawsky
|
b93f9cf14e
drm/i915: argument to control retiring behavior
|
13 years ago |
 Eugeni Dodonov
|
3d29b842e5
drm/i915: add a LLC feature flag in device description
|
13 years ago |
 Eric Anholt
|
e959b5db4a
drm/i915: Make the fallback IRQ wait not sleep.
|
13 years ago |
|
Eric Anholt
|
7ea29b13e5
drm/i915: Do the fallback non-IRQ wait in ring throttle, too.
|
13 years ago |
 Linus Torvalds
|
ed4a51842a
Revert "drm/i915: fix infinite recursion on unbind due to ilk vt-d w/a"
|
13 years ago |
|
Daniel Vetter
|
eb1711bb94
drm/i915: fix infinite recursion on unbind due to ilk vt-d w/a
|
13 years ago |
 Rakib Mullick
|
457eafce61
drm, i915: Fix memory leak in i915_gem_busy_ioctl().
|
13 years ago |
