diff options
| author | Matt Roper <[email protected]> | 2016-06-27 16:42:44 -0700 |
|---|---|---|
| committer | Matt Roper <[email protected]> | 2016-06-28 10:48:11 -0700 |
| commit | 9b6130227495fdaf17f8b3b28db083666b113c84 (patch) | |
| tree | 10e79a55c098559cdc5b7e1ed9c42bccd6654754 /tools/perf/scripts/python/event_analyzing_sample.py | |
| parent | bdaa2dfbba3e07e171bccd2404fa3f75dbc66972 (diff) | |
drm/i915/gen9: Re-allocate DDB only for changed pipes
When a display update triggers a DDB re-allocation, we should start by
assuming that only the updated pipes need to be re-allocated (we have
logic later that may add additional pipes if, e.g., a modeset triggers a
change to the global allocation).
We were erroneously using the _active_ pipes as our starting point
rather than the changed pipes. This causes us to grab CRTC locks that
we didn't actually need, reducing parallelism. Given the recent
non-blocking atomic changes, it also causes legacy pageflips against one
CRTC to return -EBUSY if there's an outstanding pageflip against a
different CRTC (a situation easily triggered via compositors like
Weston).
Fixes: 98d39494d3 ("drm/i915/gen9: Compute DDB allocation at atomic check time (v4)")
Cc: Maarten Lankhorst <[email protected]>
Signed-off-by: Matt Roper <[email protected]>
Link: http://patchwork.freedesktop.org/patch/msgid/[email protected]
Reviewed-by: Maarten Lankhorst <[email protected]>
Diffstat (limited to 'tools/perf/scripts/python/event_analyzing_sample.py')
0 files changed, 0 insertions, 0 deletions