diff options
| author | Ray Wu <ray.wu@amd.com> | 2026-08-28 10:58:39 +0800 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2026-09-17 11:38:26 -0400 |
| commit | 2f08de495c6d443a7964e30edb0e4d16597f0cfd (patch) | |
| tree | 37eabdb28393079283a2355edaf8015aa2168c39 /tools/perf/scripts/python | |
| parent | acb623f3c2fb3493e8521362e07492eb46920392 (diff) | |
| download | linux-2f08de495c6d443a7964e30edb0e4d16597f0cfd.tar.gz linux-2f08de495c6d443a7964e30edb0e4d16597f0cfd.zip | |
drm/amd/display: Flush ISM work before releasing the stream
[Why]
ISM timers are not tied to the atomic commit, so a timer armed before a
DPMS off can still fire after the stream is released. The external display
check in dcn35_apply_idle_power_optimizations() loops over the active
streams, so with none left it never runs and idle is allowed on an
external-only system.
[How]
Wait out pending and in-flight ISM work before dc_stream_release(); dc_lock
is not held there, so the sync wait is safe. Rename amdgpu_dm_ism_fini() to
amdgpu_dm_ism_flush() and assert dc_lock is not held.
Assisted-by: Cursor:Claude-Opus-5
Reviewed-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Ray Wu <ray.wu@amd.com>
Signed-off-by: Chenyu Chen <chen-yu.chen@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'tools/perf/scripts/python')
0 files changed, 0 insertions, 0 deletions
