perf: Support grouped event lists

[Andi Kleen <andi@firstfloor.org>]

As requested, this patchkit supports grouped event lists, by using
the stem as the section header. In addition it adds CPU override
support, which is useful for testing.

The updated Intel event lists with redundant entries removed are available in
git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc.git perf/intel-json-files-2

% perf list
...
icache:
  icache.hit                                        
       [Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches]
  icache.ifetch_stall                               
       [Cycles where a code-fetch stalled due to L1 instruction-cache miss or an iTLB miss]
...
idq:
  idq.all_dsb_cycles_4_uops                         
       [Cycles Decode Stream Buffer (DSB) is delivering 4 Uops]
  idq.all_dsb_cycles_any_uops                       
       [Cycles Decode Stream Buffer (DSB) is delivering any Uop]
  idq.all_mite_cycles_4_uops                        
       [Cycles MITE is delivering 4 Uops]