Re: [Xen-devel] [PATCH 2/4] xen/arm: Implement a dummy Performance Monitor for ARM32

[Julien Grall <julien.grall@xxxxxxxxxx>]

On 05/02/2014 12:01 PM, Ian Campbell wrote:
> On Thu, 2014-04-24 at 23:45 +0100, Julien Grall wrote:
>> XSA-93 (commit 0b18220 "xen/arm: Don't let guess access to Debug and 
>> Performance
>> Monitor registers") disable Performance Monitor.
>>
>> When CONFIG_PERF_EVENTS is enabled in the Linux Kernel, regardless the
>> ID_DFR0 (which tell if Perfomance Monitors Extension is implemented) the
>> kernel will try to access to PMCR.
>>
>> Therefore we tell the guest we have 0 counters. Unfortunately we must always
>> support PMCCNTR (the cycle counter): we just RAZ/WI for all PM register,
>> which doesn't crash the kernel at least.
> 
> How often does this trap occur in practice? Once at start of day? Only
> if you run perf? Or on every guest context switch? (obviously the last
> one would be bad...)

There is few calls to the perf registers during the boot (when Linux is
compiled with CONFIG_PERF_EVENTS=y).

I didn't see any usage during guest context switch. I haven't try perf.

Regards,

-- 
Julien Grall

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel