| History log of /src/sys/external/bsd/drm2/linux/linux_dma_fence.c |
| Revision | | Date | Author | Comments |
| 1.42 |
| 01-Sep-2022 |
riastradh | drm: Fix dma fence stub fix so the lock is actually initialized.
Tested but forgot to amend change before exporting to CVS again.
|
| 1.41 |
| 01-Sep-2022 |
riastradh | drm: Fix dma fence stub so it works with locking operations.
|
| 1.40 |
| 09-Apr-2022 |
riastradh | drm: Convert membar_enter/exit stragglers to membar_acquire/release.
|
| 1.39 |
| 19-Dec-2021 |
riastradh | drm: Use atomic_load_consume/relaxed to simplify code.
|
| 1.38 |
| 19-Dec-2021 |
riastradh | drm: Support 64-bit fence context and sequence numbers.
|
| 1.37 |
| 19-Dec-2021 |
riastradh | drm: Make sure dma_fence_wait gets traced too. Deduplicate.
|
| 1.36 |
| 19-Dec-2021 |
riastradh | drm: Add dtrace probes to fences.
|
| 1.35 |
| 19-Dec-2021 |
riastradh | drm: Fix signalling return value if no enable_signaling op.
|
| 1.34 |
| 19-Dec-2021 |
riastradh | drm: Use atomic_load_relaxed for fence->flags when not locked.
Shouldn't make a semantic difference on any machines we run on, but
will make sanitizers happier and emphasize to readers that the result
may not be reliable at these points.
|
| 1.33 |
| 19-Dec-2021 |
riastradh | drm: Assert dma_fence_wait internal return value.
|
| 1.32 |
| 19-Dec-2021 |
riastradh | drm: Rework timeout return code logic.
|
| 1.31 |
| 19-Dec-2021 |
riastradh | drm: Rework dma_fence_wait_any_timeout.
- Yield the first index, not the most recently signalled one.
- Check again after last wakeup.
- Make sure to return positive for nontimeout.
- Handle ip=null.
|
| 1.30 |
| 19-Dec-2021 |
riastradh | drm: Set fence->ops for stub fences too.
|
| 1.29 |
| 19-Dec-2021 |
riastradh | drm: set f_magic in the stub fence.
Author: phone <mrg@NetBSD.org>
Committer: Taylor R Campbell <riastradh@NetBSD.org>
|
| 1.28 |
| 19-Dec-2021 |
riastradh | drm: In dma_fence_wait_timeout, allow MAX_SCHEDULE_TIMEOUT.
In the Linux API, this means wait forever.
|
| 1.27 |
| 19-Dec-2021 |
riastradh | drm: Print bad timeout in dma_fence_wait_timeout kasserts.
|
| 1.26 |
| 19-Dec-2021 |
riastradh | drm: dma_fence_get allows fence to be null; fix assertion.
While here, update comments about semantics for dma_fence_get and
dma_fence_get_rcu (which does not allow null fence).
|
| 1.25 |
| 19-Dec-2021 |
riastradh | drm: Set fence timestamps -- i915 uses them.
|
| 1.24 |
| 19-Dec-2021 |
riastradh | drm: Sprinkle assertions about fence lifetime.
|
| 1.23 |
| 19-Dec-2021 |
riastradh | drm: Add a kassert for fence destruction.
|
| 1.22 |
| 19-Dec-2021 |
riastradh | drm: Skip enabling signalling for fence if already signalled.
|
| 1.21 |
| 19-Dec-2021 |
riastradh | drm: Ensure the fence callback is initialized on failure.
|
| 1.20 |
| 19-Dec-2021 |
riastradh | drm: Rework enable-signal logic to match Linux.
|
| 1.19 |
| 19-Dec-2021 |
riastradh | amdgpu_fb.c
amdgpu_fence.c
amdgpu_gart.c
amdgpu_fixpt31_32.c
amdgpu_fiji_smumgr.c
amdgpu_gem.c
amdgpu_gfx_v10_0.c
amdgpu_gfx_v6_0.c through amdgpu_gfx_v9_0.c
amdgpu_gmc.c
amdgpu_gmc_v6_0.c through amdgpu_gmc_v10_0.c
amdgpu_gtt_mgr.c
some amdgpu_h* files
some amdgpu_i* files
some amdgpu_j* files
amdgpu_kms.c
some amdgpu_m* and amdgpu_n* files
|
| 1.18 |
| 19-Dec-2021 |
riastradh | i915: Defer destroying request lock and fence until page destruction.
|
| 1.17 |
| 19-Dec-2021 |
riastradh | Add missing unlock at exit
Author: Maya Rashish <maya@NetBSD.org>
Committer: Taylor R Campbell <riastradh@NetBSD.org>
|
| 1.16 |
| 19-Dec-2021 |
riastradh | drm/dma-fence: Fix zero timeout semantics in dma_fence_default_wait.
|
| 1.15 |
| 19-Dec-2021 |
riastradh | linux dma-fence: Fix up more callback uses.
|
| 1.14 |
| 19-Dec-2021 |
riastradh | linux dma-fence: Use dma_fence_default_wait if .wait is null.
|
| 1.13 |
| 19-Dec-2021 |
riastradh | Fix typo.
|
| 1.12 |
| 19-Dec-2021 |
riastradh | Move grody i915 dma-fence hacks into dma-fence proper.
|
| 1.11 |
| 19-Dec-2021 |
riastradh | Teach dma_fence_any_wait_timeout to return index of signalled fence.
|
| 1.10 |
| 19-Dec-2021 |
riastradh | dma_fence_get_status
|
| 1.9 |
| 19-Dec-2021 |
riastradh | First approximation of dma_fence_get_stub.
|
| 1.8 |
| 19-Dec-2021 |
riastradh | Issue __insn_barrier in dma_fence_get_rcu.
This way it is safe to use as dma_fence_get_rcu(*p) when concurrent
writes to *p might be happening, so that we load *p only once before
using the value.
|
| 1.7 |
| 19-Dec-2021 |
riastradh | Allow const volatile fence pointer pointers in dma_fence_get_rcu_safe.
|
| 1.6 |
| 19-Dec-2021 |
riastradh | We spell it ELAST.
|
| 1.5 |
| 19-Dec-2021 |
riastradh | dma_fence_set_error
|
| 1.4 |
| 19-Dec-2021 |
riastradh | Linux wants to violate abstractions, so fine, let them.
|
| 1.3 |
| 19-Dec-2021 |
riastradh | Add dma_fence_get_rcu_safe.
|
| 1.2 |
| 19-Dec-2021 |
riastradh | Rename fence -> dma_fence, step 3 of 3: code.
|
| 1.1 |
| 19-Dec-2021 |
riastradh | Rename fence -> dma_fence, step 1: files.
|
