[Intel-gfx] forcewake v4 (now with spinlock)

[Ben Widawsky]

As the patches say, I don't think adding this spinlock will have too
much of a performance impact (I couldn't notice anything in my limited
testing), because the serializing locks are already held when acquiring
this lock. I suppose it now serializes access between stuct_mutex and
config.lock, but in most cases I don't think that's big.

Perhaps the ugliest change is spin_lock() in debugfs. But as I argue in
the comments, if you can't get the lock there, register reads are also
failing, and hung somewhere else.

Ben