While ~T0+T1+CF = T1-T0+CF-1 is true for the low 32-bits,
it does not produce the correct carry-out to bit 33. Do
exactly what the manual says.
Cc: Alexander Graf <agraf@suse.de>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>