summaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Expand)Author
2013-02-11sna: Fix inaccurate use of __attribute__((const))Chris Wilson
2013-02-11sna/dri: Ignore a compiler barf breaking an assertionChris Wilson
2013-02-11sna/dri: Couple up the flush pixmap after checking for allocation failuresChris Wilson
2013-02-11sna/dri: Tighten the assertions that we have one DRI2Buffer per PixmapChris Wilson
2013-02-11sna: Assert that we do not destroy a GPU bo for an active DRI pixmapChris Wilson
2013-02-11sna: Avoid stalling for changing cache levels on an active scanoutChris Wilson
2013-02-11sna/dri: Only clear the GPU bo flush flag when the last export is destroyedChris Wilson
2013-02-10sna: Restore glyphs with xorg-1.12Chris Wilson
2013-02-10sna: Reorder some includes so that compat-api.h comes after the headers it wraps2.21.1Chris Wilson
2013-02-10sna: Backport to squeeze - Xorg-1.6, pixman-0.16, libdrm-2.4.21Chris Wilson
2013-02-09sna: Fix alignment of the base of partial buffers for pre-G33 chipsetsChris Wilson
2013-02-09sna: Promote to GPU is only partially damaged on the CPU but busy on the GPUChris Wilson
2013-02-08sna: Randomly perturb 'wedged' to hunt for faultsChris Wilson
2013-02-08sna/gen6: Use GT2 settings for both GT2 and GT2+Chris Wilson
2013-02-08sna: Force the fallback path for unaccelerated randr damageChris Wilson
2013-02-08sna/gen4: Split the have_render flag in separate prefer_gpu hintsChris Wilson
2013-02-08sna: Remove the bogus assertions on buffer domainsChris Wilson
2013-02-07sna: Fixup an invalid assertionChris Wilson
2013-02-07sna: Also assert that the GPU is not wedged before continuing a batchChris Wilson
2013-02-07sna: Force GTT readback if the GPU is wedgedChris Wilson
2013-02-07sna: Allow inplace uploads to utilise GTT on LLC machinesChris Wilson
2013-02-07sna: Only try the SRC fixup into the buffer if it is CPU mappedChris Wilson
2013-02-07sna: Correctly align used buffers to the following page boundaryChris Wilson
2013-02-06sna: Fallback to non-LLC paths after an allocation failure for an LLC bufferChris Wilson
2013-02-06intel: Becareful not to match UMS against future generationsChris Wilson
2013-02-06sna: Free the handle after pwrite buffer allocation failureChris Wilson
2013-02-06sna: Flush our caches if we fail to mmap an objectChris Wilson
2013-02-06sna: Correctly handle failure to CPU map a new allocationChris Wilson
2013-02-06sna: Handle mapped buffer allocation failure for LLCChris Wilson
2013-02-06sna: Relax the buffer size assertion to only be larger than requiredChris Wilson
2013-02-06sna: Make sure we always replace io buffers before inserting into the cacheChris Wilson
2013-02-06xvmc: Add the complementary XCB_CFLAGSChris Wilson
2013-02-06configure.ac: Split out XCB libraries from `XVMCLIB` into `XCB`Paul Menzel
2013-02-05sna: Tidy buffer allocation size assertionsChris Wilson
2013-02-05sna: ValleyView uses the same scanline registers as SandyBridgeChris Wilson
2013-02-05intel: add more ValleyView PCI IDsChris Wilson
2013-02-05sna/gen4: Remove old single-thread SF w/aChris Wilson
2013-02-05sna/gen4: Disable non-rectilinear GPU span compositingChris Wilson
2013-02-04build: Make generation of gen code depend on intel-gen4asmDamien Lespiau
2013-02-04build: Use $(AM_V_GEN) to silence the assembly of gen programsDamien Lespiau
2013-02-01sna: Drop bogus refcnt assertion during kgem_bo_retire()Chris Wilson
2013-02-01sna: Do not add the INPLACE hint if we have the ASYNC hint setChris Wilson
2013-02-01sna: Assert that if we have GPU damage we have a GPU boChris Wilson
2013-02-01sna/video: Correct computation of planar frame sizeChris Wilson
2013-01-31sna/gen3+: Flush vertex threads before touching global stateChris Wilson
2013-01-31sna: Make sure the needs_flush is always accompanied by a tracking requestChris Wilson
2013-01-31sna: Remove stale assertionChris Wilson
2013-01-31sna: Pass width/height to composite for rotated displaysChris Wilson
2013-01-31sna: Remember to move scanouts to the scanout cache after retiringChris Wilson
2013-01-31sna: After removing the bo from a batch, check whether it is still busyChris Wilson