summaryrefslogtreecommitdiff
path: root/src/sna/kgem.c
AgeCommit message (Expand)AuthorFilesLines
2013-10-14sna: Assert that the mode/ring are set when marking active boChris Wilson1-0/+1
2013-10-10sna: Populate bo->size from dma-bufChris Wilson1-0/+6
2013-10-10sna: Prevent changes in tiling/pitch of existing framebuffersChris Wilson1-10/+4
2013-10-03intel: Remove dependence upon having PciInfoChris Wilson1-2/+4
2013-10-02sna: Only delete unused io buffersChris Wilson1-1/+1
2013-10-02sna: Add a few more asserts around handling of buffersChris Wilson1-1/+3
2013-09-29sna: Use the bo allocation cache for converting buffersChris Wilson1-1/+5
2013-09-29sna: Whitespace fixesChris Wilson1-3/+3
2013-09-29sna: Apply the non-relaxed fencing partial paranoia everywhereChris Wilson1-1/+5
2013-09-29sna: Resize an existing framebuffer if possibleChris Wilson1-2/+45
2013-09-28sna: Avoid reads from a GTT mmapped upload bufferChris Wilson1-1/+1
2013-09-27sna: Disable the promotion of large bo as flushChris Wilson1-7/+0
2013-09-27sna: Mark all large cached buffers as purgeableChris Wilson1-2/+1
2013-09-27sna: In desperation, query the actual available aperture spaceChris Wilson1-5/+45
2013-09-26sna: Remove a bogus assertChris Wilson1-1/+0
2013-09-25sna: Check that the bo exists before attempting to undo itChris Wilson1-0/+1
2013-09-25sna: Add a few more asserts around tracking of bo->exec vs bo->requestChris Wilson1-2/+13
2013-09-25sna: Add some DBG for early flushesChris Wilson1-8/+26
2013-09-23sna: Fix cast from u64 to pointer for 32-bit hostsChris Wilson1-1/+1
2013-09-23sna: Track CPU/GTT maps independentlyChris Wilson1-189/+100
2013-09-10sna: Disable use of Y-tiling for gen4Chris Wilson1-0/+7
2013-09-04sna: WriteThrough support is now upstreamChris Wilson1-4/+0
2013-09-03sna: Mark imported PRIME fd as starting in DOMAIN_NONEChris Wilson1-0/+1
2013-09-03sna: Add some more DBGChris Wilson1-3/+7
2013-08-16sna: Make sure that external scanouts are immediately discardedChris Wilson1-0/+8
2013-08-14Correct misspelled cachingSedat Dilek1-25/+25
2013-08-12Check for struct sysinfo as well as <sys/sysinfo.h>Julien Cristau1-2/+2
2013-08-10sna: Remove the redundant clearing of kgem at startupChris Wilson1-2/+0
2013-08-09sna: Allow LLC to reuse any active write bufferChris Wilson1-1/+1
2013-08-09sna: Check for EINVAL after mmappingChris Wilson1-0/+8
2013-08-08sna: Use create2 to allocate a DISPLAY bo even if we have not enough stolenChris Wilson1-6/+10
2013-08-08sna: Always reuse scanout bo where possibleChris Wilson1-1/+20
2013-08-08sna: Avoid leaking stolen framebuffer boChris Wilson1-28/+23
2013-08-08sna: Only use the experimental create2 if we support DISPLAY cacheing as wellChris Wilson1-1/+3
2013-08-07sna: Update experimental create2 struct definitionChris Wilson1-12/+13
2013-08-04sna: Mark the entire userptr proxy chain as flush/non-reusableChris Wilson1-0/+1
2013-07-31sna: Relax readback constraint for CPU mappings of scanoutsChris Wilson1-3/+1
2013-07-30sna: Allow CPU access to scanouts if WT cachedChris Wilson1-1/+22
2013-07-20sna: Relax assertion that CPU syncs are performed on reffed objectsChris Wilson1-2/+0
2013-07-19sna: Tidy a few DBG regarding cached uploadsChris Wilson1-0/+1
2013-07-17sna: Wrap cpuid.hChris Wilson1-12/+3
2013-07-17sna: Guard cpuid for use only with gcc-4.4 and laterChris Wilson1-1/+11
2013-07-17sna: Ensure that buffer_size is a power-of-two for use in ALIGNChris Wilson1-0/+1
2013-07-17sna: Fall back to /proc/cpuinfo parsing if cpuid cache size probe failsChris Wilson1-1/+36
2013-07-17sna: Set a minimum size for tiled IOChris Wilson1-1/+8
2013-07-16sna: Make the assumption bpp>=8 explicit inside the bo size calculationChris Wilson1-0/+1
2013-07-15sna/gen4: Allow rendering to Y-tiled surfacesChris Wilson1-4/+0
2013-07-11sna: Replace parsing of /proc/cpuinfo with parsing of cpuidChris Wilson1-23/+42
2013-07-07sna: Experiment with a new ioctl to create buffers from stolen memoryChris Wilson1-12/+110
2013-07-06sna/gen4: Restore the flush-every-vertex w/aChris Wilson1-0/+1