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@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>