[PATCH 6/6] aarch64: Add hp-timing.h

[Andrew Pinski]

On Mon, Jul 21, 2014 at 12:05 PM, Richard Henderson <rth@twiddle.net> wrote:
> On 07/21/2014 08:31 AM, Marcus Shawcroft wrote:
>> On 21 July 2014 13:01, Andreas Schwab <schwab@suse.de> wrote:
>>> pinskia@gmail.com writes:
>>>
>>>>> On Jul 21, 2014, at 4:41 AM, Andreas Schwab <schwab@suse.de> wrote:
>>>>>
>>>>> Richard Henderson <rth@twiddle.net> writes:
>>>>>
>>>>>> +/* Sync the instruction stream, and read from the virtual cycle counter.  */
>>>>>> +#define HP_TIMING_NOW(Var) \
>>>>>> +  __asm__ __volatile__ ("isb; mrs %0, cntvct_el0" : "=r" (Var))
>>>>>
>>>>> According to https://bugs.launchpad.net/bugs/1344320 the generic timers
>>>>> are not part of the kernel-to-userspace contract.
>>>>
>>>>
>>>> I think this is bogus for the kernel folks not allow a high precision timer in user space. Timers like this are needed for micro-benchmarking compiler changes along with other libc changes.
>>>
>>> According to the qemu bug the timers are optional.
>>>
>>
>> The generic timers are indeed optional, therefore we should not assume
>> they are always present.  I don't want this to ship in 2.20 as is, so
>> will back out the patch in the morning pending a better solution.
>
> Do you know of any real hardware that doesn't have the timers?  I really can't
> imagine them being elided.

More than that, right now the Linux kernel requires the timings so it
is not optional for the linux kernel.
http://lists.infradead.org/pipermail/linux-arm-kernel/2012-August/114155.html

That patch makes it sound like it is part of the kernel userland
ABI/API as it allows for a fast gettimeofday() (that does not have to
be in VDSO if I read the comment correctly).

Thanks,
Andrew Pinski

>
> It should be trivial to enable this for qemu linux-user mode; we certainly
> support the i386 rdtsc instruction.
>
>
> r~
>