diff options
| author |   fred gao <fred.gao@intel.com> | 2017-11-14 17:09:35 +0800 |
|---|---|---|
| committer |   Zhenyu Wang <zhenyuw@linux.intel.com> | 2017-11-16 11:51:55 +0800 |
| commit | f2880e04f3a5419366926182fc97a3c2e4fd8f2a (patch) | |
| tree | 99d877cb2d9f3e434fc9b3af1327972f9f15d786 /tools/perf/scripts/python/export-to-postgresql.py | |
| parent | drm/i915/gvt: Let each vgpu has separate opregion memory (diff) | |
| download | linux-dev-f2880e04f3a5419366926182fc97a3c2e4fd8f2a.tar.xz linux-dev-f2880e04f3a5419366926182fc97a3c2e4fd8f2a.zip | |
drm/i915/gvt: Move request alloc to dispatch_workload path only
Previously the performance is improved through the workload auditing
and shadowing ahead of vGPU scheduling, however, there is the case that
more requests are allocated in submit_context before the previous request
is added, the timeline will hold its seqno which is later.
This patch is to move the request alloc to dispatch_workload function,
where is the same place as request is added.
It will fix the issue of kernel BUG for (timeline->seqno != request->fence.seqno)
check when add_request.
Fixes: 89ea20b930cb ("drm/i915/gvt: Factor out scan and shadow from workload dispatch")
Signed-off-by: Chuanxiao Dong <chuanxiao.dong@intel.com>
Signed-off-by: fred gao <fred.gao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Diffstat (limited to 'tools/perf/scripts/python/export-to-postgresql.py')
0 files changed, 0 insertions, 0 deletions