summaryrefslogtreecommitdiff
AgeCommit message (Expand)AuthorFilesLines
2 min.Revert "sna: Apply scanout stride limits to tiling selection"HEADmasterChris Wilson1-11/+0
2 min.sna: Switch to a per-crtc pixmap if the pitch exceeds scanout limitationsChris Wilson1-1/+26
17 min.sna: Apply scanout stride limits to tiling selectionChris Wilson1-0/+11
89 min.sna: Assert that the scanout fits within the allocated bufferChris Wilson1-0/+1
5 hoursconfigure: test for librt (clock_gettime)Jonathan Gray4-2/+7
18 hourssna: Allow wedged pixmaps to be accessed via GTTChris Wilson1-1/+1
29 hourssna: Specialise mi calls to PolyFillRectChris Wilson1-0/+43
29 hourssna: Add extra assertions to sanity check CPU access is coherentChris Wilson4-8/+50
29 hourssna: Do not sync after a failed mappingChris Wilson1-1/+2
29 hourssna: Try falling back through an upload if inplace mapping failsChris Wilson2-36/+34
29 hourssna: Mark the base bo as unreusable for temporary mappingsChris Wilson2-2/+9
41 hourssna: Unwrap proxies for subpage offset SHM pixmaps during syncChris Wilson1-2/+8
41 hourssna: Refactor scanout flushingChris Wilson4-32/+33
4 dayssna: Be explicit in not marking an upload buffer as being on the cpuChris Wilson1-4/+6
6 dayssna/gen3+: Remove redundant clearing of clear hint in video playbackChris Wilson5-5/+0
6 dayssna: Tighten a few asserts on pixmap migrationChris Wilson1-2/+7
6 dayssna/gen7: Set sampler swizzle for video sourcesChris Wilson1-20/+28
6 dayssna/gen2+: Promote a conditional dirty into an assertionChris Wilson5-4/+13
7 dayssna: Do not enlarge the read back region if there is already CPU damageChris Wilson1-1/+5
7 dayssna/video: Free the private video (adaptor/port) arrays upon CloseScreenChris Wilson1-1/+14
7 dayssna/video: Catch allocation failure whilst setting up the TexturedAdaptorChris Wilson2-4/+6
7 dayssna: Allow the throttling to be woken by SIGINTChris Wilson1-1/+5
8 dayssna: Make sure the source is coherent on the CPU before uploadingChris Wilson1-19/+30
8 dayssna: Mollify an assert to allow us to call busy_ioctl on a GTT writeChris Wilson2-7/+10
8 dayssna: Make sure the source is coherent on the CPU before uploadingChris Wilson1-15/+16
9 dayssna: Tidy batch submission around CRTC updatesChris Wilson1-5/+1
9 dayssna: Move the GTT dirty tracking from the pixmap to the boChris Wilson5-29/+10
9 dayssna: s/bo->dirty/bo->gpu_dirty/ to avoid later confusionChris Wilson2-17/+17
9 dayssna: Make sure all sna_write_boxes* flag the GTT is dirtyChris Wilson2-5/+21
9 dayssna: Keep the cached EDID if it hasn't changedChris Wilson1-2/+14
10 dayssna: Streamline connector probingChris Wilson1-215/+277
12 dayssna: Set the needs_flush flag on the bo when the scanout is dirtyChris Wilson1-2/+6
12 dayssna: Track when we write directly to bo through the GTTChris Wilson2-2/+23
12 dayssna/dri: Check rather than assert for a change in back/front sizesChris Wilson1-5/+15
12 dayssna/dri: Fix transcription error in commit ab47433b20Chris Wilson1-1/+1
12 dayssna/dri: Do not decouple the flip after chaining up a blitChris Wilson1-3/+7
13 dayssna/video: Select vsync by default based on "SwapbuffersWait"Chris Wilson1-1/+1
13 dayssna/video: Fixup formats to select visualsChris Wilson5-9/+42
13 dayssna/dri: Make the fallback blit async againChris Wilson1-1/+1
13 dayssna/dri: Handle fast double flips across mode changesChris Wilson1-75/+67
13 dayssna: Fix format specifier for mismatching int/long in DBGChris Wilson9-13/+15
13 days2.21.9 release2.21.9Chris Wilson2-1/+23
13 dayssna: Only emit an error for terminal mmap failuresChris Wilson1-8/+16
14 dayssna: Include the GT details in the backend name for a chipsetChris Wilson2-16/+27
14 daysAdd more correct names for Haswell.Rodrigo Vivi1-14/+14
2013-06-05sna/video: Fix redundant initialisation of video->clipChris Wilson1-1/+1
2013-06-05sna: Do not conflate ignoring an output with an allocation failureChris Wilson1-5/+39
2013-06-03sna: Always populate the CPU features stringChris Wilson1-2/+4
2013-06-03sna: Make copying the glyph size more compactChris Wilson1-6/+4
2013-06-02sna/dri: Undo any COW before performing a copy with DRI2CopyRegionChris Wilson1-1/+7
[next]
generated by cgit v0.9.0.2-2-gbebe at 2013-06-19 15:17:54 (GMT)