Re: [PATCH v4] introduce macro spin_event_timeout()

[Timur Tabi <timur@freescale.com>]

On Thu, Mar 12, 2009 at 11:50 AM, Peter Zijlstra <peterz@infradead.org> wrote:
> sched_clock() does that, but:
>  - it falls back to jiffies on poor platforms

I think it's ok to fall back to jiffies where necessary, but these two
functions are too heavy-weight for my tastes.

> But something that seems to always work, is simply count loops and rely
> on whatever delay is in the specified loop.
>
> #define spin_until_timeout(condition, timeout, rc) \
>        for (unsigned long __timeout = 0; \
>             !(rc = (condition)) && __timeout < (timeout); \
>             __timeout++)

But that's the thing - I don't want a required delay inside the loop.

I guess I'm going to have to think about this for a while.  I'd like
to see something like cycles_per_usec() as a companion function to
get_cycles().

-- 
Timur Tabi
Linux kernel developer at Freescale