summaryrefslogtreecommitdiff
path: root/sys/dev
AgeCommit message (Collapse)Author
2013-03-03make the wait_seqno call in intel_ring_wait_seqno non interruptibleJonathan Gray
2013-03-03sync intel_ring_idle with 3.4.33Jonathan Gray
2013-03-03match 3.4.33 and flush in i915_gem_object_finish_gpuJonathan Gray
2013-03-02Turn "stub" debug message into a "partial stub" message.Mark Kettenis
2013-03-03move closer still to 3.4.33 in i915_gem_object_wait_renderingJonathan Gray
2013-03-02remove duplicate include linesJonathan Gray
2013-03-02move i915_gem_object_wait_rendering a bit closer to 3.4.33Jonathan Gray
2013-03-01move i915_gem_idle closer to linuxJonathan Gray
2013-03-01move i915_gem_object_unbind closer to linuxJonathan Gray
2013-03-01error out instead of asserting on invalid tiling modeJonathan Gray
until the the problem with a trashed fb obj during reboot is tracked down anyway, as this prevents having to fsck continually.
2013-03-01add i915_gem_object_flush_gtt_write_domainJonathan Gray
2013-03-01sync i915_gem_object_fence_ok with linuxJonathan Gray
2013-02-28Implement i915_gem_release_mmap() and i915_gem_object_finish_gtt(), and callMark Kettenis
them when appropriate.
2013-02-28Further reduce the differences with Linux 3.4.33 by replacing some code withMark Kettenis
a call to functions that implement the same code sequence.
2013-02-28add some additional i915_add_request calls linux makesJonathan Gray
Seems to resolve wait_seqno getting into a state where it is stuck in the gemwt msleep forever.
2013-02-28use the same hangcheck timer interval as linuxJonathan Gray
2013-02-28hook up the unpin taskJonathan Gray
2013-02-28Fix PIPE_CONTROL DW/QW write through global GTT on IVB+Jonathan Gray
backport a fix from linux: The bit controlling whether PIPE_CONTROL DW/QW write targets the global GTT or PPGTT moved moved from DW 2 bit 2 to DW 1 bit 24 on IVB. I verified on IVB that the fix is in fact effective. Without the fix none of the scratch writes actually landed in the pipe control page. With the fix the writes show up correctly. v2: move PIPE_CONTROL_GLOBAL_GTT_IVB setup to where other flags are set Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Reviewed-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-02-28make use of wakeup_pendingJonathan Gray
2013-02-28sleep/wakeup on ring rather than softc where appropriateJonathan Gray
2013-02-27indirectly pass the cache level down to agp by abusing spare bus_dma bitsJonathan Gray
2013-02-27sync more of the execbuffer code with linuxJonathan Gray
2013-02-27check interruptible directly instead of using a possibly stale varJonathan Gray
2013-02-27add back inteldrm_wipe_mappings callJonathan Gray
2013-02-27add rps tasks to the system workqJonathan Gray
2013-02-27uncomment a call to i915_handle_errorJonathan Gray
2013-02-27pte bits have changed on gen6+, for now always set to uncachedJonathan Gray
2013-02-27sync execbuffer domain tracking and flushing with linux 3.4.33Jonathan Gray
2013-02-26enable more of i915_gem_object_pin_to_display_planeJonathan Gray
2013-02-26unstub i915_gem_object_set_cache_levelJonathan Gray
2013-02-26set a default cache levelJonathan Gray
2013-02-26unstub i915_gem_object_flush_cpu_write_domainJonathan Gray
2013-02-26add a i915_gem_clflush_object implementation, not yet usedJonathan Gray
2013-02-26add some additional flushes found in linux 3.4.33Jonathan Gray
2013-02-25Bring domain handling code close to Linux 3.4.33.Mark Kettenis
2013-02-25claim to support BSD/BLT ringsJonathan Gray
2013-02-25init some vblank varsJonathan Gray
2013-02-25add some callbacks and a var for upcoming vblank changesJonathan Gray
2013-02-25enable ivybridge parity taskJonathan Gray
2013-02-25use the ring flush callbacks in the accel fb functionsJonathan Gray
2013-02-25i915_get_fence_size is no longer neededJonathan Gray
2013-02-25sync the chip reset code with linux, we can now reset more than just 965Jonathan Gray
2013-02-24Bring inactive list management closer to what Linux does.Mark Kettenis
Now we no longer call i915_gem_object_move_to_inactive() on objects that are not active.
2013-02-24Oops, really remove all places where I915_GPU_WRITE was used.Mark Kettenis
2013-02-24Change I915_GPU_WRITE into a bitfield and adjust related code to be similarMark Kettenis
to what Linux does.
2013-02-24Bring i915_gem_object_move_to_active() a bit more in line with Linux.Mark Kettenis
2013-02-24Bring i915_gem_fault() a bit more in line with the Linux code.Mark Kettenis
2013-02-24Implement i915_gem_object_is_inactive().Mark Kettenis
2013-02-24Remove #ifdef'ed out code. The replacement in i915_gem.c is here to stay.Mark Kettenis
2013-02-24Get rid of I915_FENCED_EXEC. It's effectively unused.Mark Kettenis
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-15 05:55:50 +0000