* Ivan Djelic [off-list ref] [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