[openib-general] [PATCH] mthca: memfree completion with error workaround

[Michael S. Tsirkin]

Quoting r. Roland Dreier <rdreier at cisco.com>:
> Subject: Re: [PATCH] mthca: memfree completion with error workaround
> 
> This makes me sad.  We're adding considerable code to the CQ polling
> fast path

It might not be too bad - there's a single additional test on fastpath, and I am
guessing both wqe_index and rq.max should be in registers already.
Once wqe_index is out of rq.max range we are on slow path.

> I wish there were a better way.

We can make it a compile-time option, so that users can disable it
once there's a firmware that does not need this code.

-- 
MST