Re: [PATCH] dmtimer posting

[Tony Lindgren <tony@atomide.com>]

* Woodruff, Richard <r-woodruff2@ti.com> [080321 02:01]:
> Hi
> 
> > Attached is a rev-4 with the cpu_relax() added to while loops as
> > suggested by Ladislav, and CTRL register defines moved to the right
> > location.
> 
> I confirm this version of the patch works on 3430 with latest kernel.

I'll push the rev-4 version of the patch today. The second patch needs
a bit more work still.

Tony


> I don't have by break out board for trace to get time stamps right now.
> Next week I can get that back or I can pass a kernel off to someone else
> like I was doing before.  Maybe Kevin can also make a test run on it.
> 
> If you just look the instructions trace from ETB alone, the load
> function shows up here but not in the older version.  Reason for that is
> the long stalls are not accounted for just the number of loops, and in
> non-posted mode there is nothing to loop on, just wait.  When you hook
> up ETM, it will correlate with an external time base then you get the
> actual time, and its here where you see it stalled out for a long time.
> 
> Seems like its good to commit.  Maybe someone could make sure a 1710
> works.
> 
> Regards,
> Richard W.
>