Currently we allow all DAPM contexts to determine their own bias level.
While this should in general work in most situations and will deliver the
lowest possible power it causes problems for our integration with the
card bias level as we're calling the card bias level functions for each
DAPM context even though they're card wide but don't say which CODEC
we're calling them for. Mitigate against this by forcing everything to
be in the same state.
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Acked-by: Liam Girdwood <lrg@ti.com>