These patches depend on the RFC patches enabling i915 PMU from Tvrtko: https://patchwork.freedesktop.org/series/27488/ Thus, CI failure to build them is expected. I think that my patches should be squeashed in Tvrtko's one actually. The first patch simply reorders functions and does nothing comparing to Tvrtko's patches. Next patches add fixes according to PMU API comments and clarifications from PMU aware engineers. v1: Make busy_stats refcounted instead of the whole pmu. v2: Expose cpumask for the i915 pmu to prevent creation of multiple events of the same type. Remove perf-driver level sampling. v3: Add CPUs online/offline tracking to form cpumask. v4: Add i915_pmu_enable_info debugfs entry. Introduce refcounting of event subscriptions. Dmitry Rogozhkin (5): drm/i915/pmu: reorder function to suite next patch drm/i915/pmu: serve global events and support perf stat drm/i915/pmu: introduce i915_pmu_enable_info debugfs entry drm/i915/pmu: introduce refcounting of event subscriptions drm/i915/pmu: deny perf driver level sampling of i915 PMU drivers/gpu/drm/i915/i915_debugfs.c | 9 + drivers/gpu/drm/i915/i915_drv.h | 20 +- drivers/gpu/drm/i915/i915_pmu.c | 404 +++++++++++++++++--------------- drivers/gpu/drm/i915/intel_ringbuffer.h | 5 +- include/uapi/drm/i915_drm.h | 28 ++- 5 files changed, 262 insertions(+), 204 deletions(-) -- 1.8.3.1 _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
