[PATCH v2 00/14] OMAP-GPMC related cleanup for common zImage

[Tony Lindgren]

* Ivan Djelic <ivan.djelic at parrot.com> [121010 09:40]:
> 
> I ran several mtd regression tests on a Beagle Board on your gpmc-czimage-v2 tag.
> All BCH error correcting tests passed successfully.
> 
> I occasionally had weird read errors though, especially when reading blank pages:
> the omap driver returned 512-byte sectors containing something like:
> 
> 30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff
> 30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff
> 30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff
> 30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff
> 30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff
> 30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ff30ffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> 
> instead of:
> 
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
> 
> I was able to reproduce the problem also on l2-mtd tip, albeit less often.
> The problem seems to occur quite randomly, it may be a hardware issue on
> my board...

Things like this typically happen in the GPMC timings are not correct.
Maybe add #define DEBUG to top of gpmc.c and compare the timings
before and after Afzal's patches? 

> Anyway, the ECC handling part looks OK to me.

Regards,

Tony