#
89400822 |
| 01-Sep-2022 |
riastradh <riastradh@NetBSD.org> |
drm: Fix dma fence stub fix so the lock is actually initialized.
Tested but forgot to amend change before exporting to CVS again.
|
#
d83a40f3 |
| 01-Sep-2022 |
riastradh <riastradh@NetBSD.org> |
drm: Fix dma fence stub so it works with locking operations.
|
#
f4ab16cd |
| 09-Apr-2022 |
riastradh <riastradh@NetBSD.org> |
drm: Convert membar_enter/exit stragglers to membar_acquire/release.
|
#
ece42d91 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Use atomic_load_consume/relaxed to simplify code.
|
#
bd72383d |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Support 64-bit fence context and sequence numbers.
|
#
19857f54 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Make sure dma_fence_wait gets traced too. Deduplicate.
|
#
15a96b9b |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Add dtrace probes to fences.
|
#
6412a72b |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Fix signalling return value if no enable_signaling op.
|
#
f806b9e8 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
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 resu
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.
show more ...
|
#
95ce5684 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Assert dma_fence_wait internal return value.
|
#
05cdf8b4 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Rework timeout return code logic.
|
#
ae93c501 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
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.
|
#
464621fb |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Set fence->ops for stub fences too.
|
#
07191af7 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: set f_magic in the stub fence.
Author: phone <mrg@NetBSD.org> Committer: Taylor R Campbell <riastradh@NetBSD.org>
|
#
e8433fb6 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: In dma_fence_wait_timeout, allow MAX_SCHEDULE_TIMEOUT.
In the Linux API, this means wait forever.
|
#
307b9e56 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Print bad timeout in dma_fence_wait_timeout kasserts.
|
#
c6010e2a |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
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).
|
#
b724d402 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Set fence timestamps -- i915 uses them.
|
#
f5ba9028 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Sprinkle assertions about fence lifetime.
|
#
51bebbff |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Add a kassert for fence destruction.
|
#
9c4c6364 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Skip enabling signalling for fence if already signalled.
|
#
8041567e |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Ensure the fence callback is initialized on failure.
|
#
cf0190ca |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
drm: Rework enable-signal logic to match Linux.
|
#
0caae222 |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
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 am
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
show more ...
|
#
16f1ba6c |
| 19-Dec-2021 |
riastradh <riastradh@NetBSD.org> |
i915: Defer destroying request lock and fence until page destruction.
|