Hi, I&#39;m doing a bunch of high-performance computing benchmarking on ARM -- the benchmarks and runtimes like to have a fine-grained cycle counter that is available from user space (something like MFTB on PowerPC), so I&#39;ve been using the PMU cycle counter in a similar fashion to what has been documented here: <a href="https://groups.google.com/forum/?fromgroups=#!topic/beagleboard/4VUJyOJx2r8">https://groups.google.com/forum/?fromgroups=#!topic/beagleboard/4VUJyOJx2r8</a><div>

<div><br></div><div>The downside is that I have to have a kernel module which enables it&#39;s use by user space, which complicates up-streaming ARM versions of the various benchmarks (as I don&#39;t want to have to include a kernel module with them....).</div>

</div><div><br></div><div>It would seem to me that it would be better to have a sysfs interface (or something similar) which allowed privileged users to enable/disable user-land access to the PMU in the mainstream kernel.  This could also help with arbitrating access to PMU from conflicting sources (such as trying to use the CCNT from user-space when it is being used by oprofile).</div>

<div><br></div><div>I&#39;m open to other suggestions, but if this sounds like a good idea I&#39;d be willing to draft a patch to add such an interface (assuming it doesn&#39;t already exist elsewhere and I just didn&#39;t find it with some quick greps).</div>

<div><br></div><div>Thanks,</div><div><br></div><div>     -eric</div><div><br></div>