[PATCH 1/3] mpt2sas: remove the use of writeq, since writeq is not atomic

[Moore, Eric]

On Wednesday, May 18, 2011 3:30 PM, Benjamin Herrenschmidt wrote:
> 
> You may also want to look at Milton's comments, it looks like the way
> you do init_completion followed immediately by wait_completion is racy.
> 
> You should init the completion before you do the IO that will eventually
> trigger complete() to be called.
> 

I agree.  The init_completion needs to be done prior to posting the smid.  I'm not sure why I did it that way.