summaryrefslogtreecommitdiff
path: root/src/sna/kgem.c
AgeCommit message (Expand)Author
2013-12-11sna/gen8: Initial backend for BroadwellChris Wilson
2013-12-10sna: Set minimum pitch alignment to 8 bytesChris Wilson
2013-12-03sna: Include Pineview in fence over-allocation checksChris Wilson
2013-12-02sna: Drop forced alignment to 64 on pre-gen4 devicesChris Wilson
2013-11-29sna: Dump GTT info if we fail to execute a batch due to ENOSPCChris Wilson
2013-11-28sna: Wrap image upload with sigtrapChris Wilson
2013-11-25sna: Add missing va_endZdenek Kabelac
2013-11-13Bump experimental ioctl command numbersChris Wilson
2013-11-12sna: Factor available memory into available aperture estimationChris Wilson
2013-11-09Merge branch 'master' of hsw:/usr/src/xf86-video-intelChris Wilson
2013-11-08sna: Always schedule upload buffers for retirement after useChris Wilson
2013-11-07sna: Skip an unmappable linear bo when searching through a cache for a GTT ma...Chris Wilson
2013-11-07sna: Only assert that the bo is small enough to be mmappedChris Wilson
2013-11-06sna: Add a DBG breadcrumb to kgem_bo_convert_to_gpu()Chris Wilson
2013-11-06sna: Trim create flags if tiled sizes are too largeChris Wilson
2013-11-06sna: Fences are power-of-two sizesChris Wilson
2013-11-06sna: Trim the overestimate of required aperture space for fence alignmentChris Wilson
2013-11-05sna: Submit execution on the bo before changing its caching statusChris Wilson
2013-11-05sna: Clear snoop flag after converting from a CPU boChris Wilson
2013-11-05sna: Use an inplace exchange for large untiled BOChris Wilson
2013-11-05sna: Be move conservative with tiling sizes for older fenced genChris Wilson
2013-11-04sna: s/active/busy/ to silence compiler warningChris Wilson
2013-11-04sna: Update DBG formats for larger BO offset integersChris Wilson
2013-11-04sna: Rename the two variants of pwrite so very relative dangers are obviousChris Wilson
2013-11-04sna: Use the unoptimized pwrite for general buffersChris Wilson
2013-11-02sna: Eliminate the redundancy between is_mappable/can_mapChris Wilson
2013-11-02sna: Add some more asserts around inactive VMA listsChris Wilson
2013-11-02sna: Tweak estimate of maximum usable aperture for strict fencingChris Wilson
2013-11-02Prepare for changes in the BLT unit on future generationsChris Wilson
2013-11-01sna: Scale uses of aperture_mappable by PAGE_SIZEChris Wilson
2013-10-31sna: Tweak deletion of used buffersChris Wilson
2013-10-30sna: Queue retirement when placing a BO on the deferred flushing listChris Wilson
2013-10-30sna: Check for wedged after submittingChris Wilson
2013-10-29sna: Fix assertion checks for fake flushing requestsChris Wilson
2013-10-29sna: Remove an overzealous assertChris Wilson
2013-10-29sna: Handle deferred retiring of active-buffersChris Wilson
2013-10-29sna: Always run the retire_buffers during ring_idleChris Wilson
2013-10-29sna: Perform an explicit retire for old active upload buffersChris Wilson
2013-10-29sna: Check for retired upload buffers after checking for an idle ringChris Wilson
2013-10-29sna: Try harder to complete writesChris Wilson
2013-10-28sna: And be pessimistic when checking aperture limitsChris Wilson
2013-10-28sna: Account for extra guard pages around snooped BO in aperture checksChris Wilson
2013-10-28sna: Defer opportunistic flush if all bo are current on the GPUChris Wilson
2013-10-28sna: Leave extra room in the mappable aperture for fence alignmentChris Wilson
2013-10-28sna: Use page-count for mappable aperture sizeChris Wilson
2013-10-27sna: Fallthrough to opportunistic flushing after aperture checksChris Wilson
2013-10-25sna: Trim usuable fenced aperture by unfenced usageChris Wilson
2013-10-25sna: Fix overallocation of fences for BLT commands (gen2/3)Chris Wilson
2013-10-23sna: Tidy opportunistic flushingChris Wilson
2013-10-22sna: Free bo along unlikely one-off error pathChris Wilson