[PATCH v5 3/7] arm64/perf: Changed events naming as per ARM ARM

[ashoks@broadcom.com (Ashok Kumar)]

On Wed, Apr 20, 2016 at 02:34:56PM +0100, Mark Rutland wrote:
> On Tue, Apr 19, 2016 at 11:54:18AM -0700, Ashok Kumar wrote:
> > changed all the events name definition as per ARM ARM
> > naming convention.
> 
> Please note which document you got these from (I assume the ARM ARM),
> complete with the ARM document number (e.g. ARM DDI 0487A.i for revision
> A.i). That gives us a consistent point of reference, which is helpful
> for review and in case these names have cahnged (or change in future).
> 
> I've verified that the renaming of architected events now leaves them
> named as per the ARM ARM. I see that we don't have the full list of
> IMPDEF events, but that's a matter for another patch.
> 
> It might also be worth explicitly noting the correction of the l21/l2i
> typo, as that looks a little odd otherwise.
> 
> >  /* ARMv8 Cortex-A53 specific event types. */
> >  #define ARMV8_A53_PERFCTR_PREFETCH_LINEFILL			0xC2
> >  
> >  /* ARMv8 Cavium ThunderX specific event types. */
> > -#define ARMV8_THUNDER_PERFCTR_L1_DCACHE_MISS_ST			0xE9
> > -#define ARMV8_THUNDER_PERFCTR_L1_DCACHE_PREF_ACCESS		0xEA
> > -#define ARMV8_THUNDER_PERFCTR_L1_DCACHE_PREF_MISS		0xEB
> > -#define ARMV8_THUNDER_PERFCTR_L1_ICACHE_PREF_ACCESS		0xEC
> > -#define ARMV8_THUNDER_PERFCTR_L1_ICACHE_PREF_MISS		0xED
> > +#define ARMV8_THUNDER_PERFCTR_L1D_CACHE_MISS_ST			0xE9
> > +#define ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_ACCESS		0xEA
> > +#define ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_MISS		0xEB
> > +#define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_ACCESS		0xEC
> > +#define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS		0xED
> 
> I'm not sure of the value of renaming these. I would think these should
> match whatever is in the documentation for Cortex-A53 and ThunderX
> respectively (and there's the obvious PREFETCH/PREF difference
> remaining).
I have changed them to PREF and will post it in v6.
I checked table 12.28 in Cortex-A53 MPCore Processor TRM r0p4.
For 0xc2, event mnemonic is not available but event name says 
"Linefill because of prefetch".

Thanks for the review.
> 
> However, I'll leave that to Will.
> 
> Other than that, this looks good to me:
> 
> Reviewed-by: Mark Rutland <mark.rutland@arm.com>
> 
> Thanks for putting this together!
> 
> Mark.