summaryrefslogtreecommitdiffstats
Commit message (Expand)AuthorAgeFilesLines
* Merge branch 'drm-intel-next' of git://anongit.freedesktop.org/drm-intel into...Dave Airlie2016-08-2553-3309/+4259
|\
| * io-mapping: Fixup for different names of writecombineDaniel Vetter2016-08-241-0/+6
| * io-mapping.h: s/PAGE_KERNEL_IO/PAGE_KERNEL/Chris Wilson2016-08-241-2/+2
| * drm/i915: Update DRIVER_DATE to 20160822Daniel Vetter2016-08-221-1/+1
| * drm/i915: Use remap_io_mapping() to prefault all PTE in a single passChris Wilson2016-08-195-45/+99
| * drm/i915: Embed the io-mapping struct inside drm_i915_privateChris Wilson2016-08-196-14/+13
| * io-mapping: Always create a struct to hold metadata about the io-mappingChris Wilson2016-08-191-35/+57
| * drm/i915/fbc: Allow on unfenced surfaces, for recent genChris Wilson2016-08-191-2/+4
| * drm/i915/fbc: Don't set an illegal fence if unfencedChris Wilson2016-08-191-16/+32
| * drm/i915: Flush delayed fence releases after resetChris Wilson2016-08-191-1/+5
| * drm/i915: Reattach comment, complete type specificationDave Gordon2016-08-191-2/+3
| * drm/i915/cmdparser: Accelerate copies from WC memoryChris Wilson2016-08-181-27/+43
| * drm/i915/cmdparser: Use binary search for faster register lookupChris Wilson2016-08-181-22/+20
| * drm/i915/cmdparser: Check for SKIP descriptors firstChris Wilson2016-08-181-0/+3
| * drm/i915/cmdparser: Compare against the previous command descriptorChris Wilson2016-08-181-7/+14
| * drm/i915/cmdparser: Improve hash functionChris Wilson2016-08-181-20/+31
| * drm/i915/cmdparser: Only cache the dst vmapChris Wilson2016-08-181-14/+19
| * drm/i915/cmdparser: Use cached vmappingsChris Wilson2016-08-182-81/+54
| * drm/i915/cmdparser: Add the TIMESTAMP register for the other enginesChris Wilson2016-08-181-0/+5
| * drm/i915/cmdparser: Make initialisation failure non-fatalChris Wilson2016-08-183-16/+19
| * drm/i915: Stop discarding GTT cache-domain on unbind vmaChris Wilson2016-08-181-23/+3
| * drm/i915: Bump the inactive tracking for all VMA accessedChris Wilson2016-08-181-6/+23
| * drm/i915: Track display alignment on VMAChris Wilson2016-08-182-13/+9
| * drm/i915: Fallback to using unmappable memory for scanoutChris Wilson2016-08-182-4/+14
| * drm/i915: Choose not to evict faultable objects from the GGTTChris Wilson2016-08-183-4/+16
| * drm/i915: Drop ORIGIN_GTT for untracked GTT writesChris Wilson2016-08-182-4/+10
| * drm/i915: Convert partial ggtt vma to full ggtt if it spans the entire objectChris Wilson2016-08-181-0/+6
| * drm/i915: Fix partial GGTT faultingChris Wilson2016-08-181-31/+30
| * drm/i915: Choose partial chunksize based on tile row sizeChris Wilson2016-08-181-1/+16
| * drm/i915: Move fence tracking from object to vmaChris Wilson2016-08-1812-388/+330
| * drm/i915: Rename fence.lru_list to linkChris Wilson2016-08-184-8/+7
| * drm/i915/userptr: Make gup errors stickierChris Wilson2016-08-181-10/+7
| * drm/i915: Allocate rings from stolenChris Wilson2016-08-181-4/+2
| * drm/i915: Allow ringbuffers to be bound anywhereChris Wilson2016-08-182-8/+8
| * drm/i915: Move map-and-fenceable tracking to the VMAChris Wilson2016-08-188-40/+36
| * drm/i915: Disallow direct CPU access to stolen pages for relocationsChris Wilson2016-08-181-0/+3
| * drm/i915: Fallback to single page GTT mmappings for relocationsChris Wilson2016-08-181-11/+51
| * drm/i915: Refactor execbuffer relocation writingChris Wilson2016-08-181-139/+152
| * drm/i915: Tidy up flush cpu/gtt write domainsChris Wilson2016-08-181-11/+4
| * drm/i915: Pin the pages first in shmem prepare read/writeChris Wilson2016-08-181-20/+28
| * drm/i915: Wait for writes through the GTT to land before reading backChris Wilson2016-08-181-1/+11
| * drm/i915: Before accessing an object via the cpu, flush GTT writesChris Wilson2016-08-181-0/+4
| * drm/i915: Extract i915_gem_obj_prepare_shmem_write()Chris Wilson2016-08-183-65/+102
| * drm/i915: Cache kmap between relocationsChris Wilson2016-08-181-54/+111
| * drm/i915: Fallback to single page pwrite/pread if unable to release fenceChris Wilson2016-08-182-13/+19
| * drm/i915: Mark up the GTT flush following WC writes as ORIGIN_CPUChris Wilson2016-08-181-2/+2
| * drm/i915: Use ORIGIN_CPU for fb invalidation from pwriteChris Wilson2016-08-181-2/+2
| * drm/i915: vfree() no longer ignores the low bits of the addressChris Wilson2016-08-182-4/+12
| * agp/intel: Flush chipset writes after updating a single PTEChris Wilson2016-08-181-0/+2
| * drm/i915: Unconditionally flush any chipset buffers before execbufChris Wilson2016-08-182-10/+4
OpenPOWER on IntegriCloud