Re: [PATCH] Add VDSO time function support for x86 32-bit kernel

[Andy Lutomirski <luto@amacapital.net>]

[cc: Jeremy Fitzhardinge -- you wrote some of this]

On Tue, Dec 11, 2012 at 12:40 PM, Stefani Seibold <stefani@seibold.net> wrote:
> Am Dienstag, den 11.12.2012, 11:37 -0800 schrieb Andy Lutomirski:
>> On Tue, Dec 11, 2012 at 8:11 AM,  <stefani@seibold.net> wrote:
>> > --- a/arch/x86/vdso/vclock_gettime.c
>> > +++ b/arch/x86/vdso/vclock_gettime.c
>> > @@ -59,14 +59,23 @@ notrace static cycle_t vread_tsc(void)
>> >
>> >  static notrace cycle_t vread_hpet(void)
>> >  {
>> > +#ifdef CONFIG_X86_64
>> >         return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0);
>> > +#else
>> > +       return readl(VVAR(vsyscall_hpet) + HPET_COUNTER);
>> > +#endif
>> >  }
>>
>> Is 0xf0 not equal to HPET_COUNTER?
>>
>
> Yes, but HPET_COUNTER is more readable.

Sorry -- read it backwards.  Can you change the 64-bit one as well?

>
>> >
>> >  notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
>> >  {
>> >         long ret;
>> > +#ifdef CONFIG_X86_64
>> >         asm("syscall" : "=a" (ret) :
>> >             "0" (__NR_clock_gettime),"D" (clock), "S" (ts) : "memory");
>> > +#else
>> > +       asm("int $0x80" : "=a" (ret) :
>> > +           "a" (__NR_clock_gettime), "b" (clock), "c" (ts) : "memory");
>> > +#endif
>> >         return ret;
>> >  }
>>
>> __kernel_vsyscall is probably much faster if you can figure out how to
>> call it from here :)
>>
>
> Yes i know. Thats one of my problems, because i cannot call
> __kernel_vsyscall directly due the relocation. Any idea?

What actually goes wrong?  I think that if calling __kernel_vsyscall
like a normal symbol doesn't work then it's a bug in the relocation.

What's the point of this relocation?  It appears thoroughly useless in
the !compat case.

--Andy