I was looking for a simple mechanism to measure GPU workloads, it turns out that the support is already present in the msm driver. In this series I try to make use of the hardware counters where possible for a more accurate workload estimation. Please review and share your thoughts on this. I could have piggybacked on the devfreq samples and accumulated the busytimes, but I chose not to, since it puts a dependency on the gpu devfreq which in itself is an optional feature. There is one pending issue with GPU recovery + sampling use case, which I plan to address soon. Sharat Masetty (3): drm/msm: Change gpu_busy() function drm/msm/a6xx: Move power counter selectable to resume() drm/msm: Use Hardware counters for perf profiling drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 6 +++--- drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 22 +++++++++++----------- drivers/gpu/drm/msm/msm_gpu.c | 33 ++++++++++++++++++++++++++++----- drivers/gpu/drm/msm/msm_gpu.h | 7 ++++--- drivers/gpu/drm/msm/msm_perf.c | 10 +++++----- 5 files changed, 51 insertions(+), 27 deletions(-) -- 1.9.1
