[PATCH RFC] ARM: unwind: optimize to not convert each table value but the address

[Uwe Kleine-König]

On Mon, Nov 21, 2011 at 04:34:00PM +0000, Catalin Marinas wrote:
> On Sun, Nov 20, 2011 at 11:12:42PM +0000, Uwe Kleine-König wrote:
> > The offsets in the unwind index section are signed 31 bit numbers and
> > the structs are sorted by this offset. So it first has offsets between
> > 0x40000000 and 0x7fffffff (i.e. the negative offsets) and then offsets
> > between 0x00000000 and 0x3fffffff. When seperating these two blocks the
> > numbers are sorted even when interpreting the offsets as unsigned longs.
> > 
> > So instead of converting each offset hit during bisection to an absolute
> > address, first determine which of the blocks needs to be searched and
> > then adapt the key to find for the offset while bisecting using a simple
> > unsigned long comparison.
> > 
> > In my tests this is faster than the original implementation modifying
> > the unwind index section by 4.5%.
> 
> If you don't care about the 7% unwinding performance drop on XIP
> kernels, we could just have a prel31_lt() macro (or whatever other name)
> which is a standard '<' comparison on !XIP kernels and does the prel31
> conversion with XIP. It's only two places in search_index() where it is
> needed and the code would still be more readable than the changes in
> this patch :).
> 
> If you still want such improvement, I'll do a proper review of the
> patch.
I'd prefer to get my improvement in. It took me quite some time to work
it out and I'm proud to made it work. And I don't think it's that
complicated or unreadable. Do you think it is? It's a bit different than
your code so the patch might look complicated, but IMHO the result is
fine.

If that makes your review easier, the main difference in the bisection
is that for you "last" is inclusive (at least with my optimisation) while
my "end" points behind the last entry that is considered.

Best regards
Uwe

-- 
Pengutronix e.K.                           | Uwe Kleine-König            |
Industrial Linux Solutions                 | http://www.pengutronix.de/  |