summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/i915/i915_active.c (follow)
Commit message (Expand)AuthorAgeFilesLines
* drm/i915: Extend i915_request_await_active to use all timelinesChris Wilson2020-03-111-11/+67
* drm/i915: Skip barriers inside waitsChris Wilson2020-02-281-0/+3
* drm/i915: Flush idle barriers when waitingChris Wilson2020-02-251-9/+33
* drm/i915: Drop assertion that active->fence is unchangedChris Wilson2020-02-251-1/+0
* drm/i915: Hold reference to previous active fence as we queueChris Wilson2020-02-031-1/+5
* drm/i915: Use the async worker to avoid reclaim tainting the ggtt->mutexChris Wilson2020-01-301-2/+8
* drm/i915: Fix preallocated barrier list appendJosé Roberto de Souza2020-01-301-9/+10
* drm/i915: Tighten atomicity of i915_active_acquire vs i915_active_releaseChris Wilson2020-01-271-7/+9
* drm/i915: Satisfy smatch that a loop has at least one iterationChris Wilson2020-01-171-0/+1
* drm/i915/gt: Drop mutex serialisation between context pin/unpinChris Wilson2020-01-061-4/+15
* drm/i915: Remove i915->kernel_contextChris Wilson2019-12-211-0/+2
* drm/i915: Serialise i915_active_acquire() with __active_retire()Chris Wilson2019-12-051-2/+3
* drm/i915: Serialise i915_active_wait() with its retirementChris Wilson2019-12-021-0/+1
* drm/i915: Specialise i915_active.work lock classesChris Wilson2019-12-021-2/+6
* drm/i915: Serialise i915_active_fence_set() with itselfChris Wilson2019-11-271-50/+57
* drm/i915: Mark up the calling context for intel_wakeref_put()Chris Wilson2019-11-201-2/+3
* drm/i915: Split i915_active.mutex into an irq-safe spinlock for the rbtreeChris Wilson2019-11-141-29/+28
* drm/i915/gt: Split intel_ring_submissionChris Wilson2019-10-241-0/+1
* drm/i915/gt: Introduce barrier pulses along enginesChris Wilson2019-10-211-0/+1
* drm/i915: Make for_each_engine_masked work on intel_gtTvrtko Ursulin2019-10-181-2/+2
* drm/i915: Move idle barrier cleanup into engine-pmChris Wilson2019-10-041-0/+1
* drm/i915: Coordinate i915_active with its own mutexChris Wilson2019-10-041-166/+156
* drm/i915: Push the i915_active.retire into a workerChris Wilson2019-10-041-4/+30
* drm/i915: Pull i915_vma_pin under the vm->mutexChris Wilson2019-10-041-16/+79
* drm/i915: Mark i915_request.timeline as a volatile, rcu pointerChris Wilson2019-09-201-1/+1
* drm/i915: Only activate i915_active debugobject onceChris Wilson2019-08-271-2/+6
* drm/i915: i915_active.retire() is optionalChris Wilson2019-08-191-2/+4
* drm/i915: Markup expected timeline locks for i915_activeChris Wilson2019-08-161-4/+15
* drm/i915: Serialise read/write of the barrier's engineChris Wilson2019-08-141-5/+23
* drm/i915: Lift timeline into intel_contextChris Wilson2019-08-091-3/+3
* drm/i915: Allow sharing the idle-barrier from other kernel requestsChris Wilson2019-08-021-39/+249
* drm/i915: Do not rely on for loop caching the maskTvrtko Ursulin2019-07-261-3/+3
* drm/i915: Capture vma contents outside of spinlockChris Wilson2019-07-261-1/+33
* drm/i915: Markup potential lock for i915_activeChris Wilson2019-07-031-0/+2
* drm/i915: Report if i915_active is still busy upon waitingChris Wilson2019-07-021-1/+7
* drm/i915: Provide an i915_active.acquire callbackChris Wilson2019-06-211-110/+115
* drm/i915: Track i915_active using debugobjectsChris Wilson2019-06-211-1/+65
* drm/i915: Keep engine alive as we retire the contextChris Wilson2019-06-181-2/+20
* drm/i915: Keep contexts pinned until after the next kernel context switchChris Wilson2019-06-141-0/+78
* drm/i915: Use i915_global_register()Chris Wilson2019-03-061-10/+18
* drm/i915: Make request allocation caches globalChris Wilson2019-02-281-1/+6
* drm/i915: Protect i915_active iterators from the shrinkerChris Wilson2019-02-111-11/+25
* drm/i915: Pull i915_gem_active into the i915_active familyChris Wilson2019-02-051-21/+41
* drm/i915: Allocate active tracking nodes from a slabcacheChris Wilson2019-02-051-3/+28
* drm/i915: Release the active tracker tree upon idlingChris Wilson2019-02-051-10/+23
* drm/i915: Generalise GPU activity trackingChris Wilson2019-02-051-0/+228