Quoting Tvrtko Ursulin (2018-09-17 12:28:12) > From: Lionel Landwerlin <lionel.g.landwerlin@xxxxxxxxx> > > Verify that the per-context dynamic SSEU uAPI works as expected. > > To achieve that, in the absence of a better mechamism, we read the value > of PWR_CLK_STATE register, or use MI_SET_PREDICATE on platforms before > Cannonlake. > > This register is written to by the GPU on context restore so this way > we verify i915 is correctly updating the context image in all > circumstances. > > v2: Add subslice tests (Lionel) > Use MI_SET_PREDICATE for further verification when available (Lionel) > > v3: Rename to gem_ctx_rpcs (Lionel) > > v4: Update kernel API (Lionel) > Add 0 value test (Lionel) > Exercise invalid values (Lionel) > > v5: Add perf tests (Lionel) > > v6: Add new sysfs entry tests (Lionel) > > v7: Test rsvd fields > Update for kernel series changes > > v8: Drop test_no_sseu_support() test (Kelvin) > Drop drm_intel_*() apis (Chris) > > v9: by Chris: > Drop all do_ioctl/do_ioctl_err() > Use gem_context_[gs]et_param() > Use gem_read() instead of mapping memory > by Lionel: > Test dynamic sseu on/off more > > Tvrtko Ursulin: > > v10: > * Various style tweaks and refactorings. > * New test coverage. > > v11: > * Change platform support to just Gen11. > * Simplify availability test. (Chris Wilson) > * More invalid pointer tests. (Chris Wilson) > > v12: > * Fix MAP_FIXED use (doh!). > * Fix get/set copy&paste errors. > * Drop supported platform test. (Chris Wilson) > * Add mmap__gtt test. (Chris Wilson) > > v13: > * Commit message tweaks. > * Added reset/hang/suspend tests. (Chris Wilson) > * Assert spinner is busy. (Chris Wilson) > * Remove some more ABI assumptions. (Chris Wilson) > > v14: > * Use default resume time. (Chris Wilson) > * Trigger hang after rpcs read batch has been submitted. (Chris Wilson) > > Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@xxxxxxxxx> > Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx> I can't think of any other mechanism that could interfere with ctx-sseu that isn't being tested, Reviewed-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> -Chris _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
