On 09-02-22, 21:01, Bjorn Andersson wrote: > The OSM and EPSS hardware controls the frequency of each cluster in the > system based on requests from the OS and various limiting factors, such > as input from LMH. > > In most systems the vote from the OS is done using a single register per > cluster, but some systems are configured to instead take one request per > core. In this configuration a set of consecutive registers are used for > the OS to request the frequency of each of the cores within the cluster. > The information is then aggregated in the hardware and the frequency for > the cluster is determined. > > As the current implementation ends up only requesting a frequency for > the first core in each cluster and only the vote of non-idle cores are > considered it's often the case that the cluster will be clocked (much) > lower than expected. > > It's possible that there are benefits of performing the per-core > requests from the OS, but more investigation of the outcome is needed > before introducing such support. As such this patch extends the request > for the cluster to be written to all the cores. > > The weight of the policy's related_cpus is used to determine how many > cores, and hence consecutive registers, each cluster has. > > The OS is not permitted to disable the per-core dcvs feature. > > Signed-off-by: Bjorn Andersson <bjorn.andersson@xxxxxxxxxx> > --- > drivers/cpufreq/qcom-cpufreq-hw.c | 18 ++++++++++++++++++ > 1 file changed, 18 insertions(+) Applied. Thanks. -- viresh
