Log - 3f3333f8a0e90ac26f84ed7b0aa344efce695c08 - kernel/msm-4.19

636918f drm/i915: Mark the GT as busy before idling the previous request by Chris Wilson · 7 years ago
535275d drm/i915: Squelch reset messages during selftests by Chris Wilson · 7 years ago
77b25a9 drm/i915: Make i915_gem_context_mark_guilty() safe for unlocked updates by Chris Wilson · 7 years ago
4d53568 drm/i915: Move idle checks before intel_engine_init_global_seqno() by Chris Wilson · 7 years ago
7b92c1b drm/i915: Avoid keeping waitboost active for signaling threads by Chris Wilson · 7 years ago
6b56708 drm/i915: Remove the spin-request during execbuf await_request by Chris Wilson · 8 years ago
9f90ff3 drm/i915: Check signaled state after enabling signaling by Chris Wilson · 8 years ago
1d5fd00 drm/i915: Remove misleading comment in request_alloc by Michał Winiarski · 8 years ago
6c06757 drm/i915: Split execlist priority queue into rbtree + linked list by Chris Wilson · 8 years ago
266a240 drm/i915: Use engine->context_pin() to report the intel_ring by Chris Wilson · 8 years ago
49f0859 drm/i915: Switch the global i915.semaphores check to a local predicate by Chris Wilson · 8 years ago
fc9d4d2 drm/i915: Do not record a successful syncpoint for a dma-await by Chris Wilson · 8 years ago
7e8894e drm/i915: Rename intel_timeline.sync_seqno[] to .global_sync[] by Chris Wilson · 8 years ago
4797948 drm/i915: Squash repeated awaits on the same fence by Chris Wilson · 8 years ago
ceae14b drm/i915: Lift timeline ordering to await_dma_fence by Chris Wilson · 8 years ago
29ef3fa drm/i915: Unwrap top level fence-array by Chris Wilson · 8 years ago
f7b02a5 drm/i915: Skip waking the signaler when enabling before request submission by Chris Wilson · 8 years ago
e6ba999 drm/i915: Differentiate between sw write location into ring and last hw read by Chris Wilson · 8 years ago
ade0b0c drm/i915: Confirm the request is still active before adding it to the await by Chris Wilson · 8 years ago
b0fd47a drm/i915: Copy user requested buffers into the error state by Chris Wilson · 8 years ago
cbb60b4 drm/i915: Advance ring->head fully when idle by Chris Wilson · 8 years ago
2ca9faa drm/i915: Assert the engine is idle before overwiting the HWS by Chris Wilson · 8 years ago
ae351be drm/i915: Combine reset_all_global_seqno() loops into one by Chris Wilson · 8 years ago
7a453fb drm/i915: Remove redudant wait for each engine to idle from seqno wrap by Chris Wilson · 8 years ago
72022a7 drm/i915: Move retire-requests into i915_gem_wait_for_idle() by Chris Wilson · 8 years ago
05506b5 drm/i915: Use a dummy timeline name for a signaled fence by Chris Wilson · 8 years ago
fe085f1 drm/i915: Remove intel_ring.last_retired_head by Chris Wilson · 8 years ago
8c185ec drm/i915: Split I915_RESET_IN_PROGRESS into two flags by Chris Wilson · 8 years ago
2e16101 Merge tag 'drm-intel-next-2017-03-06' of git://anongit.freedesktop.org/git/drm-intel into drm-next by Dave Airlie · 8 years ago
5400367 drm/i915: Ensure the engine is idle before manually changing HWS by Chris Wilson · 8 years ago
c8659ef drm/i915: Drop spinlocks around adding to the client request list by Chris Wilson · 8 years ago
6752041 drm/i915: s/assert_spin_locked/lockdep_assert_held/ by Chris Wilson · 8 years ago
e60a870 drm/i915: Assert that fence->lock is held in an irq-safe manner by Chris Wilson · 8 years ago
f361bf4 sched/headers: Prepare for the reduction of <linux/sched.h>'s signal API dependency by Ingo Molnar · 8 years ago
e601757 sched/headers: Prepare for new header dependencies before moving code to <linux/sched/clock.h> by Ingo Molnar · 8 years ago
56299fb drm/i915: Signal first fence from irq handler if complete by Chris Wilson · 8 years ago
0f2f61d drm/i915: Remove one level of indention from wait-for-execute by Chris Wilson · 8 years ago
24f417e drm/i915: Immediately process a reset before starting waiting by Chris Wilson · 8 years ago
e070511 drm/i915: Refactor direct GPU reset from request waiters by Chris Wilson · 8 years ago
a49625f drm/i915: Replace reset_wait_queue with default_wake_function by Chris Wilson · 8 years ago
d6a2289 drm/i915: Remove the preempted request from the execution queue by Chris Wilson · 8 years ago
754c9fd drm/i915: Protect the request->global_seqno with the engine->timeline lock by Chris Wilson · 8 years ago
fe49789 drm/i915: Deconstruct execute fence by Chris Wilson · 8 years ago
541ca6e drm/i915: Inline __i915_gem_request_wait_for_execute() by Chris Wilson · 8 years ago
7de53bf drm/i915: Add ourselves to the gpu error waitqueue for the entire wait by Chris Wilson · 8 years ago
4b36b2e drm/i915: Use a local to shorten req->i915->gpu_error.wait_queue by Chris Wilson · 8 years ago
12d3173 drm/i915: Move reserve_seqno() next to unreserve_seqno() by Chris Wilson · 8 years ago
9b6586a drm/i915: Keep a global seqno per-engine by Chris Wilson · 8 years ago
354d036 drm/i915/tracepoints: Add request submit and execute tracepoints by Tvrtko Ursulin · 8 years ago
9369250 drm/i915/tracepoints: Tidy i915_gem_request_wait_begin by Tvrtko Ursulin · 8 years ago
c33ed06 drm/i915: Break i915_spin_request() if we see an interrupt by Chris Wilson · 8 years ago
44a0270 drm/i915: Check for timeout completion when waiting for the rq to submitted by Chris Wilson · 8 years ago
73dec95 drm/i915: Emit to ringbuffer directly by Tvrtko Ursulin · 8 years ago
c835c55 drm/i915: Add selftests for i915_gem_request by Chris Wilson · 8 years ago
969bb72 drm/i915: Check for timeout completion when waiting for the rq to submitted by Chris Wilson · 8 years ago
6ffb7d0 drm/i915: Construct a request even if the GPU is currently hung by Chris Wilson · 8 years ago
c781c97 drm/i915: Add a sanity check that no request is submitted in the middle by Chris Wilson · 8 years ago
a402eae Merge tag 'v4.10-rc2' into drm-intel-next-queued by Daniel Vetter · 8 years ago
f73e739 drm/i915: Swap if(enable_execlists) in i915_gem_request_alloc for a vfunc by Chris Wilson · 8 years ago
e8a9c58 drm/i915: Unify active context tracking between legacy/execlists/guc by Chris Wilson · 8 years ago
9439b37 Merge tag 'drm-for-v4.10' of git://people.freedesktop.org/~airlied/linux by Linus Torvalds · 8 years ago
0e932c0 drm/i915: Hold a reference on the request for its fence chain by Chris Wilson · 8 years ago
fc15840 drm/i915: Integrate i915_sw_fence with debugobjects by Chris Wilson · 8 years ago
48bc2a4 drm/i915: Hold a reference on the request for its fence chain by Chris Wilson · 8 years ago
1618bdb drm/i915: Assert no external observers when unwind a failed request alloc by Chris Wilson · 8 years ago
4ffd6e0 drm/i915: Add is-completed assert to request retire entrypoint by Chris Wilson · 8 years ago
4c266ed drm/i915: Rename i915_gem_timeline.next_seqno to .seqno by Joonas Lahtinen · 8 years ago
bc1d53c drm/i915: Wipe hang stats as an embedded struct by Mika Kuoppala · 8 years ago
e5e1fc4 drm/i915: Use request retirement as context progress by Mika Kuoppala · 8 years ago
786d290 drm/i915: Check that each request phase is completed before retiring by Chris Wilson · 8 years ago
4302055 drm/i915: Be more careful to drop the GT wakeref by Chris Wilson · 8 years ago
f2f09a4 locking/core: Remove cpu_relax_lowlatency() users by Christian Borntraeger · 8 years ago
9f792eb drm/i915: Store the execution priority on the context by Chris Wilson · 8 years ago
20311bd drm/i915/scheduler: Execute requests in order of priorities by Chris Wilson · 8 years ago
52e5420 drm/i915/scheduler: Record all dependencies upon request construction by Chris Wilson · 8 years ago
0de9136 drm/i915/scheduler: Signal the arrival of a new request by Chris Wilson · 8 years ago
d55ac5b drm/i915: Defer transfer onto execution timeline to actual hw submission by Chris Wilson · 8 years ago
23902e4 drm/i915: Split request submit/execute phase into two by Chris Wilson · 8 years ago
bb89485 drm/i915: Create distinct lockclasses for execution vs user timelines by Chris Wilson · 8 years ago
6a5d1db drm/i915: Spin until breadcrumb threads are complete by Chris Wilson · 8 years ago
5bd11a3 drm/i915: Avoid early GPU idling due to already pending idle work by Imre Deak · 8 years ago
80b204b drm/i915: Enable multiple timelines by Chris Wilson · 8 years ago
f2d1329 drm/i915: Defer setting of global seqno on request to submission by Chris Wilson · 8 years ago
28176ef drm/i915: Reserve space in the global seqno during request allocation by Chris Wilson · 8 years ago
85e17f5 drm/i915: Move the global sync optimisation to the timeline by Chris Wilson · 8 years ago
caddfe7 drm/i915: Defer breadcrumb emission by Chris Wilson · 8 years ago
98f29e8 drm/i915: Record space required for breadcrumb emission by Chris Wilson · 8 years ago
9b81d55 drm/i915: Rename ->emit_request to ->emit_breadcrumb by Chris Wilson · 8 years ago
65e4760 drm/i915: Introduce a global_seqno for each request by Chris Wilson · 8 years ago
4680816b drm/i915: Wait first for submission, before waiting for request completion by Chris Wilson · 8 years ago
73cb970 drm/i915: Combine seqno + tracking into a global timeline struct by Chris Wilson · 8 years ago
d07f0e5 drm/i915: Move GEM activity tracking into a common struct reservation_object by Chris Wilson · 8 years ago
4c7d62c drm/i915: Markup GEM API with lockdep asserts by Chris Wilson · 8 years ago
e95433c drm/i915: Rearrange i915_wait_request() accounting with callers by Chris Wilson · 8 years ago
b52992c drm/i915: Support asynchronous waits on struct fence from i915_gem_request by Chris Wilson · 8 years ago
f54d186 dma-buf: Rename struct fence to dma_fence by Chris Wilson · 8 years ago
3b3f165 drm/i915: Allocate intel_engine_cs structure only for the enabled engines by Akash Goel · 8 years ago
9b05a60 drm/i915: Distinguish last emitted request from last submitted request by Chris Wilson · 8 years ago
8687b3e drm/i915: Distinguish last emitted request from last submitted request by Chris Wilson · 8 years ago
0a046a0 drm/i915: Nonblocking request submission by Chris Wilson · 8 years ago