[PATCH v8 RFC 0/3] Generic IOMMU pooled allocator

[David Miller]

From: Sowmini Varadhan <sowmini.varadhan at oracle.com>
Date: Tue, 31 Mar 2015 21:08:18 -0400

> I'm starting to wonder if  some approximation of dma premapped
> buffers may be needed. Doing a map/unmap on each packet is expensive.

It's much more amortized with smart buffering strategies, which are
common on current generation networking cards.

There you only eat one map/unmap per "PAGE_SIZE / rx_pkt_size".

Maybe the infiniband stuff is doing things very suboptimally, and
actually with that subsystem and drivers absolutely nothing would
surprise me.