trace/hwlat: Implement the per-cpu mode

Implements the per-cpu mode in which a sampling thread is created for
each cpu in the "cpus" (and tracing_mask).

The per-cpu mode has the potention to speed up the hwlat detection by
running on multiple CPUs at the same time, at the cost of higher cpu
usage with irqs disabled. Use with care.

[
  Changed get_cpu_data() to static.
Reported-by: kernel test robot <lkp@intel.com>
]

Link: https://lkml.kernel.org/r/ec06d0ab340e8460d293772faba19ad8a5c371aa.1624372313.git.bristot@redhat.com

Cc: Phil Auld <pauld@redhat.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Kate Carcia <kcarcia@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: Clark Willaims <williams@redhat.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "...